report
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific CLI tools to gather information.
- Evidence: Exercises
task list,task show,gh pr list, andherdr agent listto collect status data. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (GitHub PRs and task stores) that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Reads external input via
task list,task show, andgh pr list(SKILL.md). - Boundary markers: Absent; there are no explicit delimiters or warnings to the model to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill environment possesses command execution capabilities (CLI tools).
- Sanitization: Absent; the skill does not specify any filtering or validation of the retrieved task or PR content before summarization.
Audit Metadata