devils-advocate
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input (plans, targets, or file content) which creates a surface for indirect prompt injection. A malicious plan could contain instructions to divert the agent or abuse available tools. \n
- Ingestion points: The
$ARGUMENTSvariable and content from files identified in arguments inSKILL.md.\n - Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions within the plan content.\n
- Capability inventory: The skill dispatches to sub-agents and uses tools for research, exploration, and work-item tracking (e.g.,
/discovery:research,/discovery:explore,/work-items:track).\n - Sanitization: None.\n- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection to execute shell commands when the skill is loaded.\n
- Evidence: The skill executes
git branch --show-currentandgit log --oneline -5inSKILL.mdto establish context.
Audit Metadata