planning-goal
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious instructions, obfuscation, or hardcoded credentials detected in the skill metadata or body.
- COMMAND_EXECUTION (SAFE): The skill utilizes hooks to execute benign
echocommands during the planning lifecycle. The availability of theBashtool is aligned with the skill's purpose for managing deployment and refactoring workflows. - PROMPT_INJECTION (SAFE): No attempts to override agent behavior, bypass safety filters, or extract system prompts were identified. The instructional content follows standard functional patterns.
- INDIRECT_PROMPT_INJECTION (SAFE): The skill defines a surface for processing user-provided goal and state data (in SKILL.md). While explicit boundary markers and sanitization logic are not defined in the documentation, the skill does not contain instructions that would trigger or facilitate an injection attack.
Audit Metadata