Back to skill

Security audit

spark-media

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scans found no AIG issues, while Skillspector flagged external API requests and a missing warning about image uploads; these appear related to the skill’s media purpose, but the evidence is incomplete.

Before installing, check that you trust the configured API provider and avoid sending sensitive images or prompts unless you are comfortable sharing them. The overall verdict is benign, but Skillspector’s scan was partial because it could not resolve a local reference, so the evidence is not complete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/HTTP-REQUESTS.md (reported line 6)May include surrounding context.

bash
API_ROOT="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net}/api/v1"

curl --fail-with-body "$API_ROOT/spark-media/image" \
  -H "Authorization: Bearer ${AI_SKILLS_API_KEY:-$SPARK_MEDIA_API_KEY}" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: image-uuid-001" \

Instructions to submit local images lack a third-party data-transfer warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The text instructs users to embed complete local images in API request bodies, using the external service configured on line 4 by default. It does not warn that the full image contents will leave the user's system; base64 encoding does not protect their privacy.

Content

No source excerpt is available for this finding.