docs-architect

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebases, which represents a surface for indirect prompt injection attacks. Malicious instructions could be embedded in the code (e.g., within comments, documentation, or string literals) to influence the agent's behavior.
  • Ingestion points: Analyzes files and structure within existing codebases as described in the documentation process (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions found within the analyzed data.
  • Capability inventory: The skill performs file system analysis and produces long-form content, which could be leveraged if an injection is successful.
  • Sanitization: There is no evidence of content sanitization or validation of the ingested code snippets before they are processed or included in output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:29 AM
Security Audit — agent-trust-hub — docs-architect