alterlab-pra-brand-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a senior brand analyst role focused on strategic frameworks and market research. Analysis of the instructions and workflow in SKILL.md revealed no malicious commands, persistence mechanisms, or unauthorized data access.
- [INDIRECT_PROMPT_INJECTION]: The skill maintains an attack surface for indirect prompt injection by processing untrusted data from the web and project files.
- Ingestion points: External web search results and local project context files (e.g., brand guidelines, prior audits) referenced in the 'Workflow' and 'Agentic Protocol' sections of SKILL.md.
- Boundary markers: None; the skill does not specify delimiters or instructions to ignore embedded commands within ingested data.
- Capability inventory: The skill possesses capabilities for web searching, reading local files, and writing new markdown files as defined in SKILL.md.
- Sanitization: No procedures are described for sanitizing or validating external content before it is processed by the agent.
Audit Metadata