grant-naming-authority
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon data from untrusted files within the repository.
- Ingestion points: The agent is directed to read repository-specific files such as
AGENTS.md,CLAUDE.md, and external documentation/ADRs. It also performs a recursivegrepacross the entire project tree to identify markers. - Boundary markers: Absent. There are no instructions to use delimiters or ignore potential commands embedded within the documentation or code files being scanned.
- Capability inventory: The skill allows the agent to write markers back to the filesystem, generate pull request tables, and interact with other skills like
approval-policy. - Sanitization: Absent. The skill does not define any validation or filtering for the content retrieved from the repository files before it is processed by the agent.
Audit Metadata