stacked-delivery
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process data from external pull request descriptions to identify parent/child relationships.
- Ingestion points: Pull request descriptions and metadata in the repository environment (SKILL.md, Workflow step 1).
- Boundary markers: None. The skill does not define specific delimiters or instructions to ignore embedded commands within the PR descriptions it processes.
- Capability inventory: The skill manages Git branch lifecycles, including branching, rebasing, and force-pushing (Rules section).
- Sanitization: There is no mention of sanitizing or validating the content retrieved from PR descriptions before using it to structure the stack.
Audit Metadata