assess-docs-links

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from documentation roots and a specification file (../../specs/artifact-contract.md) to build a link graph. This creates a surface for indirect prompt injection where instructions hidden within documentation could potentially affect the agent's logic during processing.
  • Ingestion points: Documentation files (Markdown/Wiki) and project specification files.
  • Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded in the data.
  • Capability inventory: The skill is restricted to file system read and write operations; it does not have network access or the ability to execute shell commands.
  • Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 05:42 AM
Security Audit — agent-trust-hub — assess-docs-links