audit-code

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as its primary purpose is to ingest and analyze external code and documentation.
  • Ingestion points: The skill reads codebases, PR diffs, and product specifications (referenced in SKILL.md and references/audit-framework.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the code being audited.
  • Capability inventory: The skill primarily performs analytical tasks and generates reports, though it operates within the agent's default tool environment.
  • Sanitization: There is no evidence of sanitization or filtering of the ingested content to neutralize potential injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 10:45 AM
Security Audit — agent-trust-hub — audit-code