goal
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the execution of arbitrary shell commands and file modifications based on inputs, which could be exploited if malicious instructions are provided in the 'Check' or 'Goal' parameters.\n
- Ingestion points: The 'Goal' and 'Check' variables defined in the 'Inputs' section of SKILL.md.\n
- Boundary markers: Absent. The skill does not provide markers to separate intent from potentially malicious data in the check command.\n
- Capability inventory: The skill uses tools to run commands (Step 2 and 4 of Procedure) and edit files (Step 3 of Procedure).\n
- Sanitization: Absent. The skill relies on the agent to interpret and execute the user-provided check without validation or sanitization.
Audit Metadata