skill-safety-audit
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a meta-utility for security auditing. It provides a methodology for identifying malicious patterns in other skills, such as remote downloads, secret exposure, and unjustified privilege escalation. It explicitly forbids dangerous behaviors such as running installers, network transfers, or privilege escalation during the audit process.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as its primary function is to ingest and analyze potentially untrusted skill files and scripts.
- Ingestion points: The skill analyzes 'Changed skill entrypoints and bundled resources' and 'New dependency or endpoint provenance' (SKILL.md).
- Boundary markers: The skill does not define specific boundary markers for the data it processes, though it instructs the agent to treat findings as data rather than instructions.
- Capability inventory: The skill is restricted to 'read' and 'search' operations on the filesystem (SKILL.md).
- Sanitization: No explicit sanitization or escaping mechanisms for the analyzed content are defined in the instructions.
Audit Metadata