co-marketing

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is configured to ingest project-specific marketing context from local files if they exist in the environment. This creates an indirect prompt injection surface where untrusted data from these files could potentially influence agent behavior.
  • Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (as referenced in SKILL.md).
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided when reading these files.
  • Capability inventory: No dangerous tools such as subprocess execution, dynamic code evaluation, or network exfiltration tools are defined or used within the skill's scripts.
  • Sanitization: There is no evidence of sanitization or validation of the ingested content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 12:49 AM
Security Audit — agent-trust-hub — co-marketing