plan-review-performance
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to evaluate project plans, which often come from external or untrusted sources. There are no explicit boundary markers or instructions to isolate this external data from the skill's logic, which could allow malicious instructions inside a plan to influence the agent's behavior.
- Ingestion points: Project 'plan' content analyzed by the agent (SKILL.md).
- Boundary markers: Absent; there are no delimiters defined to separate user input from system instructions.
- Capability inventory: The skill allows the use of 'Bash', 'Read', 'Grep', and 'Glob', which provides a significant capability tier if an injection were to occur.
- Sanitization: No sanitization or validation of the analyzed plans is provided in the skill instructions.
Audit Metadata