marketing-content-creator

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via ingestion of external data. \n- Ingestion points: The skill utilizes WebFetch and WebSearch to retrieve information from the internet (SKILL.md). \n- Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted web content from system instructions. \n- Capability inventory: The skill possesses Read, Write, and Edit capabilities (SKILL.md). \n- Sanitization: No mechanisms for sanitizing or filtering external content are specified. \n- [NO_CODE]: This skill consists entirely of configuration and role definitions in markdown and YAML format, with no included executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — marketing-content-creator