grill-issue
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interpolates raw user input into its workflow without boundary markers or sanitization.
- Ingestion points: User input is ingested via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: Absent. The input is not delimited (e.g., using XML tags or triple quotes) to prevent the agent from interpreting instructions within the input.
- Capability inventory: The skill has the capability to modify Linear issue statuses and delegate tasks to the
/grill-with-docsskill. - Sanitization: Absent. There is no validation or filtering of the content provided in
$ARGUMENTSbefore it is processed by the agent.
Audit Metadata