influencer-marketing-manager

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is composed exclusively of markdown documentation (SKILL.md and references/playbook.md). No executable scripts, binary files, or automated system commands are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by instructing the agent to process external creator intelligence and outreach responses. 1. Ingestion points: Creator discovery metrics and candidate communication (references/playbook.md). 2. Boundary markers: No explicit delimiters or safety instructions for untrusted data are provided. 3. Capability inventory: The skill defines no dangerous tools, network operations, or file system modifications. 4. Sanitization: No validation or filtering of external content is specified. The risk is considered safe as the skill lacks actionable capabilities for an injection to exploit.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:30 AM
Security Audit — agent-trust-hub — influencer-marketing-manager