triage
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted data from external issue trackers.\n
- Ingestion points: Reads issue titles, bodies, and comments from the project issue tracker (SKILL.md).\n
- Boundary markers: None identified. The instructions do not specify the use of delimiters or ignore-instructions for external content.\n
- Capability inventory: The skill can execute shell commands/tests, write files to the
.out-of-scope/directory, and post comments to the issue tracker.\n - Sanitization: No sanitization or filtering of external issue content is mentioned before it is processed.\n- [COMMAND_EXECUTION]: During the bug reproduction step in
SKILL.md, the agent is instructed to "run tests or commands" based on the reporter's provided steps. This pattern involves executing code influenced by untrusted external input, which could lead to arbitrary command execution if a malicious report is processed.
Audit Metadata