feature-tracking
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to runjqfor extracting statistics and filtering feature data fromdocs/blueprint/feature-tracker.json. It also suggests the use ofajv-clifor JSON schema validation. These commands are standard for the skill's data management tasks. - [DATA_EXFILTRATION]: The skill operates entirely on local project assets, including
REQUIREMENTS.md,TODO.md, and the feature tracker JSON. There is no evidence of network activity or attempts to send data externally. - [PROMPT_INJECTION]: The skill reads and processes content from project documents like
REQUIREMENTS.mdandTODO.mdto update the feature tracker. This category identifies a vulnerability to indirect prompt injection. Ingestion points:REQUIREMENTS.md,TODO.md,feature-tracker.json. Boundary markers: None identified. Capability inventory: File read/write/edit viaRead,Write,Edit, andBash(jq, ajv). Sanitization: None identified.
Audit Metadata