specialist-lenses

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed entirely of markdown reference files providing dossiers on various marketing specialists. It does not contain any executable code, network operations, or sensitive data access patterns.- [NO_CODE]: Analysis of the skill structure confirms the absence of any scripts (Python, JavaScript, Shell) or dependency manifests (package.json, requirements.txt). The skill functions as a static knowledge base for the AI agent.- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to read local context files.
  • Ingestion points: .agents/marketing-strategy.md, .agents/marketing-learnings.md, and other local marketing context files.
  • Boundary markers: Absent; the skill does not define specific delimiters for these files.
  • Capability inventory: None; the skill does not include any tools, shell commands, or network capabilities.
  • Sanitization: Absent; the skill relies on the agent's internal safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 09:00 PM