promo-brief

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill consumes untrusted data from external sources (GitHub, websites, and documentation) and processes it to generate creative briefs. This creates a surface for indirect prompt injection if the target content contains malicious instructions designed to hijack the agent's logic.
  • Ingestion points: The agent is instructed to fetch and analyze content from user-provided URLs in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions found within the crawled content.
  • Capability inventory: The skill utilizes file system write capabilities to save output to outputs/promo-runs/<product>/01-brief.md.
  • Sanitization: No sanitization or validation logic is specified for the ingested external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:56 AM
Security Audit — agent-trust-hub — promo-brief