debug
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process untrusted external content such as bug reports, error messages, and issue tickets, which creates a surface for indirect prompt injection.
- Ingestion points: Input provided via the
argument-hint(bug reports, tickets, error messages) inSKILL.mdand referenced external ticket systems (Linear). - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The agent is instructed to reproduce failures, which involves executing code, running tests, and interacting with the local environment and version control (
git log,git blame) as described inSKILL.mdworkflows. - Sanitization: No explicit sanitization or validation of the input data is described in the skill instructions.
Audit Metadata