agent-config-audit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing untrusted workspace files (e.g., AGENTS.md, CLAUDE.md, .cursorrules). This creates an attack surface where malicious instructions embedded in those files could attempt to influence the agent's behavior during the audit process.
  • Ingestion points: The skill uses glob and grep to scan numerous workspace configuration files as specified in SKILL.md (Step 1 and Step 2).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these files.
  • Capability inventory: The skill possesses file read/write capabilities (in fix mode) and shell execution capabilities (glob, grep).
  • Sanitization: No specific sanitization or validation of the content of the audited files is described before it is processed or reported to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:10 AM
Security Audit — agent-trust-hub — agent-config-audit