coding-standards

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external sources, specifically project files and existing coding standard documents.
  • Ingestion points: The skill is instructed to read the user-specified path, root CODING_STANDARDS.md, and project configuration files (CI, linters, formatters) in SKILL.md (Process steps 1 and 2).
  • Boundary markers: There are no explicit delimiters or instructions defined to prevent the agent from following instructions potentially embedded within the data files it reads.
  • Capability inventory: The skill instructions involve reading from and writing to the local filesystem.
  • Sanitization: No explicit sanitization or validation of the input content is mentioned, although the risk is significantly mitigated by a mandatory human-in-the-loop requirement for all file modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 11:53 PM
Security Audit — agent-trust-hub — coding-standards