land
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads project specification files (
docs/specs/<slug>.md) and incorporates their content into core project files such asARCHITECTURE.md,CONTEXT.md, and new Architecture Decision Records (ADRs). It also uses these specifications to generate PR descriptions and merge commit messages. - Ingestion points: Project specification files stored in
docs/specs/*.md. - Capability inventory: The skill executes Git commands (merge, branch deletion, worktree removal) and performs file system writes to update documentation and create new ADR files.
- Boundary markers: The instructions do not specify the use of delimiters or provide the agent with instructions to disregard embedded commands when processing content from the specification files.
- Sanitization: There is no explicit requirement for the agent to sanitize or validate the specification content before it is used to modify the project's permanent records or generate metadata.
Audit Metadata