libvlc
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions allow the agent to inspect the repository context and execute build, test, and validation commands. This creates a surface for indirect prompt injection, where malicious instructions embedded in project files could influence the agent's behavior during debugging or code review tasks.\n
- Ingestion points: Repository context (SKILL.md).\n
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore instructions found within the analyzed repository files.\n
- Capability inventory: The skill can edit files and run build/test/validation commands (SKILL.md).\n
- Sanitization: No specific input sanitization or content validation logic is described for the ingested repository data.\n- [SAFE]: The documentation proactively includes security best practices, specifically alerting developers to risks of exfiltration and unauthorized file access when passing untrusted data to the libvlc_media_add_option function (libvlc-skill.md).
Audit Metadata