example-command
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: Documentation of a command that ingests untrusted user data via the $ARGUMENTS variable, creating an unmitigated attack surface for prompt injection instructions.
- Ingestion points: $ARGUMENTS placeholder in SKILL.md.
- Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore malicious instructions within arguments.
- Capability inventory: The skill instructions allow the agent to use allowed tools to perform actions based on the provided arguments.
- Sanitization: Absent; there is no validation or filtering of user input described in the instructions.
Audit Metadata