implementation-planner
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project documentation and feature design specifications to generate an implementation plan for a coding agent. An attacker who can influence the project files could potentially inject instructions into the generated task list.\n
- Ingestion points: Project documentation located in
.monkeycode/docs/and design specifications located in.monkeycode/specs/.\n - Boundary markers: The skill does not define clear delimiters or provide instructions to the model to treat the ingested file content as untrusted data.\n
- Capability inventory: The skill has the ability to write a persistent
tasklist.mdfile to the file system and interact with the user to confirm the plan.\n - Sanitization: No sanitization, escaping, or validation is performed on the content read from the external documentation files before it is processed by the agent.
Audit Metadata