technical-writing

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to fetch and analyze content from external, untrusted URLs.
  • Ingestion points: Untrusted data enters the agent context via web_fetch or web_search tools in Phase 2 of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings when processing the retrieved content.
  • Capability inventory: The skill uses web_fetch, web_search, and file-writing capabilities via present_files.
  • Sanitization: No evidence of input validation, sanitization, or filtering of the external content before processing was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 05:58 PM
Security Audit — agent-trust-hub — technical-writing