specs-review

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests that the user install missing peer dependencies from the b12consulting/skills repository using the npx skills add command. This is a standard procedure within the vendor's documentation ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill audits project-specific files (such as Vision.md, PRD.md, and source code) to detect drift and inconsistencies. Processing untrusted project data creates a surface where hidden instructions could attempt to redirect the agent's behavior.
  • Ingestion points: Reads files from the specs/ directory and analyzes codebase dependencies and structure (e.g., specs/README.md, specs/Vision.md, Architecture/README.md).
  • Boundary markers: Not present. The instructions do not define specific delimiters to separate external data from system instructions.
  • Capability inventory: The skill has the ability to propose and execute file modifications, such as updating the project's README.md or creating new ADR (Architecture Decision Record) documents.
  • Sanitization: There are no explicit sanitization or validation steps mentioned for the content retrieved from the project's filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 06:26 PM