product-planner

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary functionality involves reading and writing product documentation to a local docs/ directory. It does not attempt to access sensitive system files or credentials.
  • [EXTERNAL_DOWNLOADS]: The skill mentions external tools such as CodeRabbit and links to the BuilderOS GitHub repository for additional resources. These references are contextually relevant to the skill's purpose and target well-known developer services.
  • [COMMAND_EXECUTION]: The skill instructions do not contain any arbitrary shell command execution, subprocess spawning, or piped remote script patterns (e.g., curl | bash). All file operations are handled through standard agent file system interactions.
  • [PROMPT_INJECTION]: The instructions use natural language to define the agent's persona and logic flow. No patterns were found that attempt to bypass safety filters or override the underlying AI's core instructions.
  • [DATA_EXFILTRATION]: There is no evidence of instructions that collect sensitive information for transmission to external servers. The network references found are informational links to documentation and project repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:44 PM
Security Audit — agent-trust-hub — product-planner