shepherd
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external pull request sources which may contain untrusted instructions.
- Ingestion points: The agent reads PR check state, failure logs, and review comments via the
forge shepherdcommand as described inSKILL.md. - Boundary markers: The instructions do not define delimiters or system-level directives to ignore instructions embedded within the PR data.
- Capability inventory: The skill has access to
Bash,Read,Grep, andGlobtools, enabling file system interaction and shell execution that could be influenced by injected content. - Sanitization: There is no mention of input validation or sanitization for the ingested strings before they are incorporated into the agent's context.
Audit Metadata