branded-content
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard text processing and file management tasks within the user's workspace. It reads local creative guidelines and writes generated markdown files to designated output folders. No evidence of data exfiltration, credential harvesting, or malicious code execution was found.- [PROMPT_INJECTION]: The skill ingests user-provided briefs to generate content, which creates a surface for indirect prompt injection where malicious instructions embedded in a brief could influence the agent's behavior. However, this is a standard capability for writing assistants and is mitigated by instructions to preserve confidentiality.
- Ingestion points: User-supplied brand briefs in Step 2 of the workflow.
- Boundary markers: None specified in the instructions.
- Capability inventory: Reading and writing local markdown files.
- Sanitization: Instructions require filtering confidential data, but no automated sanitization is present.
Audit Metadata