apex
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing user-provided input through the direct interpolation of arguments.
- Ingestion points: Untrusted data enters the agent context through the
{{args}}variable inSKILL.md. - Boundary markers: Absent; the skill does not use delimiters or provide specific instructions to the agent to disregard instructions potentially embedded within the user input.
- Capability inventory: The skill's environment in
SKILL.mdis configured with a broad set of tools, includingBash,Write,Edit,WebFetch, andWebSearch, which could be exploited if an injection attack is successful. - Sanitization: No sanitization, validation, or escaping logic is applied to the
{{args}}content before it is used to drive routing decisions.
Audit Metadata