btw
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by accepting arbitrary user input via the
$ARGUMENTSvariable and directing the agent to add these requirements to the active execution queue.\n - Ingestion points: Untrusted user data enters the agent context through the
$ARGUMENTSplaceholder in theSKILL.mdfile.\n - Boundary markers: The input is enclosed in backticks within the instructions, which provides minimal syntactic separation but does not prevent the agent from being influenced by instructions embedded within the user's text.\n
- Capability inventory: The skill is intended to manage 'command sequences' and an 'active execution queue', which typically involves access to high-privilege capabilities such as file modification and shell command execution in AI agent environments.\n
- Sanitization: There are no instructions or mechanisms provided to sanitize, validate, or treat the user-provided requirements as untrusted data before they are incorporated into the workflow.
Audit Metadata