plan-antislop
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed as a planning and auditing tool. It explicitly prohibits automated rewrites or code modifications, requiring user approval for each phase of its generated burndown plan.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it audits untrusted codebase content and user-facing copy. However, the risk is mitigated by its limited capabilities: it only generates a markdown report (
plan-antislop.md) and does not execute code, perform network requests, or modify existing files based on the audited data. - Ingestion points: Processes files, strings, and UI components within a provided codebase (SKILL.md).
- Boundary markers: Instructions require the agent to quote only the minimum necessary content to identify "tells" rather than processing entire files, and strictly limits actions to planning only.
- Capability inventory: No subprocess calls, no exec/eval, no network operations, and no writing to source files; only emits a planning document.
- Sanitization: Employs minimal quoting and a structured report template to prevent control flow issues.
Audit Metadata