workflow-analyze
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input via the $ARGUMENTS variable to generate a task analysis document. This creates a surface for indirect prompt injection (Category 8) where a malicious task description could attempt to influence the agent's behavior during the analysis phase. * Ingestion points: $ARGUMENTS in SKILL.md is used to define the task description. * Boundary markers: The user input is delimited within a markdown code block. * Capability inventory: The skill allows writing files to the local filesystem (docs/work/{task-name}/analysis.md). * Sanitization: There is no explicit instruction to sanitize the input or ignore instructions contained within the user-provided text.
- [NO_CODE]: The skill consists exclusively of markdown instructions and a document template. It does not include or execute any scripts, binaries, or external code.
Audit Metadata