Back to skill

Security audit

ia-orchestrating-swarms

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence; scanners found possible mismatches between its stated swarm-coordination purpose and some documented tasks, while the listed findings were judged expected for that purpose.

The verdict is benign, with medium confidence. The scan reports complete coverage of 24 components, though Skillspector also reported serializer warnings and an exit status of 1. Before installing, consider whether the documented skill-evaluation and environment-setup tasks fit your expectations for a swarm-coordination skill.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied commands target evaluation and diagnosis of the named skill. They show no agent coordination, parallel execution, pipeline construction, or subagent delegation. As presented, this is a materially different purpose, not merely an implementation detail supporting the declared workflow. The script's internal behavior is not supplied, so no additional capabilities are inferred.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

Although the code uses a subagent, its requested task is environment display configuration. The supplied chunk contains no parallel agents, pipeline stages, review coordination, or task decomposition. Its concrete purpose therefore differs materially from the declared swarm-orchestration purpose.

Content

No source excerpt is available for this finding.

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/context-carry-forward.md (reported line 11)May include surrounding context.

md
| **Rewind** | `Esc Esc` (double-escape); keeps the useful prefix, drops the tail | Recovering from a failed attempt. Drops the failure from context without losing the useful reads that came before it. Beats "correcting" in place because correction keeps the failed path visible. |
| **/compact** | Lossy summarization into a short digest | Long sessions where the earlier turns no longer matter but their conclusions do |
| **Subagent** | Spawn a subagent for the task; only the result returns to main context | Contained research, focused implementation, or anything that would balloon main-thread context |
| **/clear + brief** | Clear context; restart with a hand-written brief | Mode switch (different feature, different skill needed). Cleaner than compaction when you know what still matters. |

## Why Rewind is underused

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/environment-config.md (reported line 83)May include surrounding context.

bash
# Check team config
cat ~/.claude/teams/{team}/config.json | jq '.members[] | {name, agentType, backendType}'

# Check teammate inboxes
cat ~/.claude/teams/{team}/inboxes/{agent}.json | jq '.'

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/spawn-backends.md (reported line 149)May include surrounding context.

bash
# See what backend was detected
cat ~/.claude/teams/{team}/config.json | jq '.members[].backendType'

# Check if inside tmux
echo $TMUX

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/environment-config.md (reported line 86)May include surrounding context.

md
cat ~/.claude/teams/{team}/config.json | jq '.members[] | {name, agentType, backendType}'

# Check teammate inboxes
cat ~/.claude/teams/{team}/inboxes/{agent}.json | jq '.'

# List all teams
ls ~/.claude/teams/

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/environment-config.md (reported line 92)May include surrounding context.

md
ls ~/.claude/teams/

# Check task states
cat ~/.claude/tasks/{team}/*.json | jq '{id, subject, status, owner, blockedBy}'

# Watch for new messages
tail -f ~/.claude/teams/{team}/inboxes/team-lead.json

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/environment-config.md (reported line 95)May include surrounding context.

cat ~/.claude/tasks/{team}/*.json | jq '{id, subject, status, owner, blockedBy}'

Watch for new messages

tail -f ~/.claude/teams/{team}/inboxes/team-lead.json

text