plan-arbiter
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily focused on the logic of arbitration and normalization of text-based plans. It does not contain any executable scripts, binary files, or commands that interact with the system in a dangerous way.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process content from various external and potentially untrusted sources.
- Ingestion points: According to
SKILL.md, the agent collects plans from "pasted text, local files, session IDs, transcript paths, PRs, comments, visual-plan links, or chat history." - Boundary markers: No specific delimiters or instructions to ignore embedded commands are mandated for the plan content being analyzed.
- Capability inventory: The skill does not define custom scripts; its capabilities are constrained to the standard tools provided by the agent's environment.
- Sanitization: There is no explicit requirement or logic for sanitizing or escaping the content retrieved from external sources before it is processed.
Audit Metadata