competitor-ads-analyst

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes advertising content from external platforms, creating a potential surface for indirect prompt injection.
  • Ingestion points: Ad copy and headlines from Facebook, Google, TikTok, and LinkedIn libraries as described in SKILL.md.
  • Boundary markers: Absent; no instructions are provided to the agent to disregard instructions potentially embedded in the scraped ad copy.
  • Capability inventory: The skill contains analytical instructions but does not provide any dangerous scripts or system-level access tools.
  • Sanitization: Absent; there are no mechanisms described for filtering or sanitizing the ingested ad data.
  • [EXTERNAL_DOWNLOADS]: The skill's documentation includes a reference to a GitHub repository for installation: https://github.com/thatrebeccarae/claude-marketing.git. This resource originates from the skill's identified author.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:25 AM
Security Audit — agent-trust-hub — competitor-ads-analyst