analyze
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: User-provided input via the $ARGUMENTS placeholder is interpolated directly into the agent instructions without sanitization or boundary markers, creating a surface for potential behavior override.
- Ingestion points: $ARGUMENTS variable in SKILL.md.
- Boundary markers: Absent; user input is not delimited or clearly separated from the system instructions.
- Capability inventory: The agent has access to Bash, Read, Glob, Grep, and Task tools, which represent significant capabilities if compromised.
- Sanitization: Absent; no validation or filtering is applied to the arguments before they are processed by the agent.
Audit Metadata