documentation-extraction

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its primary function is to process and act upon untrusted external data sources.
  • Ingestion points: Project documentation including README files, API documentation, technical specifications, and configuration files (e.g., .env, package.json, config.yaml) as defined in SKILL.md.
  • Boundary markers: Absent. The skill lacks instructions for the agent to use delimiters or to treat code blocks/commands within external documents as untrusted content.
  • Capability inventory: The instructions explicitly direct the agent to "test documented commands and examples" and "run documented examples", which effectively bridges external data to command execution capabilities.
  • Sanitization: Absent. There are no mechanisms described for validating, escaping, or filtering content extracted from documentation before the agent attempts to execute or interpret it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:44 AM