sanity-check
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): The skill uses the '!' prefix to execute shell commands directly on the host system.
- Evidence: Execution of
git status,make lint, andgo testwithinSKILL.md. - Risk: Running
makeis inherently risky as it executes instructions defined in aMakefilethat could be maliciously crafted in an untrusted repository. - [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted tool output.
- Ingestion points: Results from
git,make, andgoare piped into the agent's context for analysis. - Boundary markers: Absent. There are no delimiters or instructions to ignore embedded commands in the tool output.
- Capability inventory: The skill possesses shell execution capabilities via the '!' syntax.
- Sanitization: Absent. The output is analyzed raw without escaping or validation.
Audit Metadata