Skills
Navigate
skills/yinxe/skills/web-docs-to-skill/Gen Agent Trust Hub

web-docs-to-skill

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from documentation URLs.
  • Ingestion points: The skill fetches content from user-provided URLs using webfetch and browser-use as described in SKILL.md.
  • Boundary markers: There are no instructions or delimiters specified to ensure the agent ignores instructions potentially embedded within the documentation content.
  • Capability inventory: The agent has capabilities to write files, execute shell scripts (scripts/extract-links.sh), and run Python scripts (scripts/extract_content.py).
  • Sanitization: No sanitization or validation of the fetched content is performed before it is used to generate a new skill.
  • [EXTERNAL_DOWNLOADS]: The skill uses tools like webfetch and browser-use to retrieve content from external URLs provided by the user.
  • [COMMAND_EXECUTION]: The skill executes local scripts (scripts/extract-links.sh and scripts/extract_content.py) to automate link extraction and content parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 07:54 AM
Security Audit — agent-trust-hub — web-docs-to-skill