docs-discovery

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: Technical documentation and llms.txt content are ingested from external websites using the WebFetch tool in Step 3.
  • Boundary markers: The skill does not explicitly define delimiters (such as XML tags or unique markers) to separate untrusted web content from its internal instructions.
  • Capability inventory: The skill is limited to documentation discovery, parsing, and presentation, with no high-risk capabilities like file system modification or privilege escalation triggered by fetched data.
  • Sanitization: There is no specified sanitization or validation logic for the fetched documentation strings before they are presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 06:46 AM