wiki-policy-check

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to read and process the full content of untrusted markdown files within a repository.
  • Ingestion points: Reads CLAUDE.md, AGENTS.md, and every .md file in the repository.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific warnings to the agent to ignore instructions embedded within the files being audited.
  • Capability inventory: File listing and reading (read-only). The skill explicitly lacks the ability to modify files, execute shell commands, or perform network operations.
  • Sanitization: Absent. There is no logic provided to filter or escape instructions found within the audited content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:57 PM