write-plans
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input (plan requests) and interpolate that data into structured markdown files within the repository. This creates an attack surface where an adversary could embed malicious instructions within a plan request to influence the agent's behavior during the plan execution phase.
- [SAFE]: No obfuscation, hardcoded credentials, unauthorized network calls, or suspicious shell command executions were found. The skill operates strictly within the local repository context using standard file system operations.
Audit Metadata