specs-ws

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external content from the local repository to generate documentation, creating a surface for indirect prompt injection.
  • Ingestion points: Reads multiple project files including docs/product/business-flow.md, docs/standards/tech-stack-rule.md, docs/standards/directory-rule.md, and directories docs/specs/API/, docs/product/demo/, and docs/specs/data/ (identified in SKILL.md and templates/ws-spec-prompt.md).
  • Boundary markers: The skill does not explicitly use delimiters or instruction-override guards when passing file content to subagents.
  • Capability inventory: The skill has the capability to write files to the local file system (docs/specs/ws/<module>.yaml) and interact with the user via AskUserQuestion (identified in SKILL.md Step 2 and 3).
  • Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 02:49 PM
Security Audit — agent-trust-hub — specs-ws