triage
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from GitHub issue and PR bodies, comments, and diffs to perform triage tasks.
- Ingestion points: Reading full issue/PR content (Step 1 in SKILL.md).
- Boundary markers: Absent. The skill does not use delimiters or instructions to ignore embedded commands in the source data.
- Capability inventory: The skill is instructed to "reproduce [bugs] from the reporter's steps" and "run the relevant tests or commands" for PRs, providing a path for untrusted input to influence shell execution.
- Sanitization: Absent. There is no evidence of filtering or validation for the instructions extracted from issues or the code in pull requests.
- [COMMAND_EXECUTION]: The skill requires broad command execution capabilities to interact with the environment. It uses the GitHub CLI (
gh) to list issues and is explicitly tasked with running arbitrary tests or reproduction steps provided by external contributors, which inherently carries risk when automated.
Audit Metadata