ad-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product descriptions and external project briefs to generate creative ad strategies, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill takes input from a "product X" description and a "PRODUCT-BRIEF.md" file, as specified in the logic of Parts 1 and 2.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded control sequences within the ingested product data.
  • Capability inventory: The skill is instructed to save the resulting creative brief to the local file system (e.g., at campaigns/<product-slug>/brief.md).
  • Sanitization: No explicit input validation or sanitization routines are mentioned for the processing of external product data.
  • [NO_CODE]: The skill consists entirely of instructional markdown and configuration files, with no executable scripts or binaries provided for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:00 AM
Security Audit — agent-trust-hub — ad-strategy