c-location
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection due to processing untrusted location data.
- Ingestion points: User-provided search queries and location names in SKILL.md.
- Boundary markers: Absent; no delimiters are used to separate user data from instructions.
- Capability inventory: Execution of system commands via the goplaces CLI.
- Sanitization: Absent; the skill does not specify any validation for location inputs.
- [COMMAND_EXECUTION]: The skill relies on the goplaces CLI to perform tasks. If the agent interpolates natural language location strings directly into the CLI command without proper shell escaping, it could allow for arbitrary command execution on the host macOS system.
Audit Metadata