intentline-audit
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing a Python package directly from the vendor's GitHub repository using
pip install git+https://github.com/grove/intentline.git. This is a vendor-owned resource used for the skill's primary function. - [COMMAND_EXECUTION]: The agent is instructed to invoke the
intentlineCLI tool to create audit records using the commandpython -B -m intentline audit-record --work WORK --report audit.json --json. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data such as original requests, manifests, and source code revisions.
- Ingestion points: Reads original byte-preserved requests, manifests, selected contexts, and source bundles (SKILL.md).
- Boundary markers: None explicitly defined for the ingested data content within the instructions.
- Capability inventory: Executes
python -B -m intentline audit-record(SKILL.md). - Sanitization: No explicit sanitization or validation of the input data content is described prior to the audit process, which is typical for a data analysis tool.
Audit Metadata