Back to skill

Security audit

CI Tools Monthly Digest

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported findings concern declared-scope ambiguity, an English-only digest, and a subprocess call, with no confirmed harmful behavior; confidence is medium and inspection was partial because a referenced path was missing.

Consider the undeclared network and shell scope, the English-only digest requirement, and the flagged subprocess call before installing. The scan covered all four listed components, but overall analysis was partial because a local path-like reference in SKILL.md could not be resolved; the results do not establish what that path refers to. The benign verdict is not a guarantee of zero risk.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill mandates English output without user opt-in or a documented justification.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

The workflow explicitly requires the entire digest, including headings, to be written in English. It provides neither a language choice nor a documented reason that justifies overriding the user's preferred language.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/collect.py (reported line 51)May include surrounding context.

python
seen = set()
    while True:
        query = urlencode({**params, "per_page": PAGE_SIZE, "page": page})
        result = subprocess.run(
            ["glab", "api", f"{BASE}/{endpoint}?{query}"],
            check=True, capture_output=True, text=True, timeout=30,
        )

The automation requires an English-language digest without explicit user opt-in or a documented justification.

Low
Category
Output Handling
Confidence
97% confidence
Finding

Both the job description and agent payload explicitly require an English digest. The configuration provides no language choice, explicit opt-in, or justification for fixing the output language.

Content

No source excerpt is available for this finding.