audit-agents
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly instructional and focused on document auditing. No malicious code or patterns were detected.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from AGENTS.md and README.md (Workflow step 1). Although it lacks explicit boundary markers and sanitization, its limited capabilities (text processing and file writing) prevent the exploitation of common injection payloads. Mandatory Evidence Chain: (1) Ingestion points: AGENTS.md and README.md; (2) Boundary markers: Absent; (3) Capability inventory: Text analysis and writing to the local AGENTS.md file (no subprocess, network, or eval calls); (4) Sanitization: Absent.
Audit Metadata