triage
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from GitHub issue reports and comments which can influence the agent's subsequent actions. This creates a surface for indirect prompt injection.
- Ingestion points: GitHub issue bodies, comments, and reporter-provided reproduction instructions as specified in SKILL.md.
- Boundary markers: Absent. No delimiters or security warnings are used to isolate untrusted data from the skill's own instructions.
- Capability inventory: Command execution (tests and scripts), file system modification in the .out-of-scope directory, and network-based issue management via GitHub API.
- Sanitization: Absent. The skill does not validate or sanitize instructions provided by issue reporters before acting on them.
- [COMMAND_EXECUTION]: The skill's reproduction workflow explicitly instructs the agent to "run tests or commands" based on the "reporter's steps." This allows untrusted data from an external source to directly influence shell execution, creating a security risk if the agent operates in a non-sandboxed environment.
Audit Metadata