wiki-qa

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user queries and instructs the agent to read file contents based on those queries.
  • Ingestion points: User questions regarding the codebase are processed at runtime to drive search and read operations.
  • Boundary markers: The skill uses simple negative constraints ('ONLY use information from actual source files', 'NEVER invent') but lacks robust delimiters to separate user data from instructions.
  • Capability inventory: The skill leverages file search and read capabilities which are necessary for its function but can be abused.
  • Sanitization: No evidence of path validation or sanitization is provided in the skill instructions to prevent directory traversal or access to sensitive configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:45 PM
Security Audit — agent-trust-hub — wiki-qa