campaign-brief
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests context from several files within the
knowledge/directory, including personas, market positioning, and competitors. If these files contain malicious instructions, they could influence the agent's planning process or tool calls. - Ingestion points:
knowledge/icp/personas.md,knowledge/services/,knowledge/markets/positioning.md,knowledge/markets/competitors.md,knowledge/kpis.md,knowledge/learnings.md, andknowledge/company.md. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following directions potentially embedded within the ingested knowledge files.
- Capability inventory: The skill is configured to write files to the
output/campaign-brief/directory and is designed to trigger other tools like/linkedin-postand/ppt-maker. - Sanitization: The skill employs a
[UNVERIFIED]tagging system to track data reliability for business metrics, but this does not provide protection against adversarial instructions in the input text.
Audit Metadata