release
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
just releasecommand to perform version tagging and publishing operations. - [COMMAND_EXECUTION]: The skill executes an external Python script (
utilities/skill-builder/scripts/record_skill_feedback.py) to log telemetry data after execution. - [DATA_EXFILTRATION]: Metadata regarding the skill's performance and user decisions is passed as arguments to a local feedback recording utility.
- [PROMPT_INJECTION]: The skill processes user-provided version strings which are interpolated directly into shell commands. Ingestion points: target version input and Cargo.toml file. Boundary markers: absent. Capability inventory: subprocess execution of 'just' and 'python3'. Sanitization: instructions include a requirement to ensure the target is a valid semver string.
Audit Metadata