copywriting

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and local files to perform its tasks.
  • Ingestion points: The workflow explicitly instructs the agent to use Read, WebSearch, and WebFetch to analyze project documentation, competitor copy, and platform trends.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instruction' warnings for the content being processed.
  • Capability inventory: Across its allowed-tools, the skill has the ability to Write and Edit files, creating a path for potential unauthorized file modifications if the agent obeys instructions hidden in fetched content.
  • Sanitization: No sanitization or validation steps are defined for the data retrieved via web tools or local file reads.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 07:59 PM