triage-asc-issue
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
sosumi.ai, a non-standard third-party documentation mirror, for explanatory context regarding Apple APIs. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues and comments which could contain malicious instructions.
- Ingestion points: Fetches live issue body and comments from GitHub (SKILL.md).
- Boundary markers: None specified in the instructions to distinguish between the triage instructions and the issue content.
- Capability inventory: Executes CLI commands for reproduction, performs network reads, and writes GitHub labels/comments (SKILL.md).
- Sanitization: No explicit sanitization or filtering of the fetched issue content is described.
- [COMMAND_EXECUTION]: The skill requires the ability to execute the project's own CLI for behavior reproduction.
- Evidence: "Reproduce reported behavior with the current built or installed CLI when safe" (SKILL.md).
Audit Metadata