paw-wbc-agent-producer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes research insights and briefs from external files which may contain untrusted content. If these source files contain malicious instructions, they could influence the agent's content generation or file-writing tasks.
- Ingestion points: Reads research data from
brief.md,research-context.md, andhook-selected.mdlocated in the webinar workspace. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or 'ignore instructions' warnings when processing these inputs.
- Capability inventory: The skill is capable of writing multiple files to the local file system (
slide-deck-outline.md,script.md,recommendations.md, and activity logs) and supports a--headlessmode that reduces user oversight during execution. - Sanitization: No explicit sanitization or validation of the ingested data is defined in the response protocol.
- [NO_CODE]: The skill consists exclusively of markdown instructions and reference data (CSV). It does not include or execute any scripts (Python, JavaScript, Shell, etc.), which significantly limits the risk of traditional malware behavior or remote code execution.
Audit Metadata