campaign-brief-generator

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of Markdown instructions and reference documentation. There are no executable scripts, binaries, or configuration files provided.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill is designed to read from a local file named .claude/brand-context.md to gather brand-specific details for the brief generation. This is an intended feature for personalization and does not involve accessing system-sensitive paths (such as SSH keys or cloud credentials) or exfiltrating data to external servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes user-provided inputs and content from local context files. However, the risk is negligible as the skill lacks high-privilege capabilities such as shell execution or network access.
  • Ingestion points: User inputs via prompt and the .claude/brand-context.md file.
  • Boundary markers: No explicit delimiters or boundary markers are used to isolate untrusted data.
  • Capability inventory: The skill is restricted to text generation; it has no access to subprocesses, network tools, or file-writing operations.
  • Sanitization: No explicit sanitization or validation of input data is performed before interpolation into the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 06:36 PM