longform
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow directs the agent to run a local script (scripts/ari.mjs) and a data check (data/weakeners.json) from a related righter skill to automate mechanical writing checks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-supplied long-form content, which creates a surface for instructions embedded in the data to influence the agent. (1) Ingestion points: User-provided drafts in the review and drafting workflows. (2) Boundary markers: No explicit boundary markers or wrappers are defined for user data. (3) Capability inventory: Command execution via the local script scripts/ari.mjs and file system access. (4) Sanitization: No sanitization of the input draft content is specified.
Audit Metadata