campaign-plan

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it interpolates untrusted data from local configuration files into its reasoning process.
  • Ingestion points: The skill reads multiple files including ~/.claude-marketing/brands/_active-brand.json, profile.json, _manifest.json, and files within ~/.claude-marketing/sops/.
  • Boundary markers: Absent; there are no instructions or delimiters used to prevent the agent from following commands embedded within the brand data or SOPs.
  • Capability inventory: The skill utilizes the ingested data to architecturalize campaigns, select media channels, and set performance benchmarks.
  • Sanitization: Absent; the skill does not perform validation or filtering on the content of the JSON and Markdown files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 10:34 AM