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.md file 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
Risk Level
SAFE
Analyzed
Aug 15, 2026, 07:03 PM
Security Audit — agent-trust-hub — implementation-planner