harness-docs-maintain

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is instructed to read untrusted data from project repositories to verify and update documentation.
  • Ingestion points: The skill reads docs/index.md, source code, configuration files, and test files as part of its verification procedure.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" markers are defined to prevent the agent from executing instructions found within the project files.
  • Capability inventory: The skill possesses file-write capabilities for updating documentation and can execute the harness-artifact and harness-docs-audit tools.
  • Sanitization: The instructions do not specify any sanitization, escaping, or validation of the content read from the project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:37 PM
Security Audit — agent-trust-hub — harness-docs-maintain