product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data from the repository's codebase to automatically draft a marketing context document.\n
  • Ingestion points: Reading codebase files (README, landing pages, package.json, etc.) in Step 2: Gather Information.\n
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat the ingested codebase content as untrusted or to ignore instructions within those files.\n
  • Capability inventory: The skill uses file-read and file-write capabilities but lacks network access or subprocess execution.\n
  • Sanitization: No validation or sanitization of the ingested content is performed before processing it into the marketing document.\n- [NO_CODE]: This skill consists entirely of natural language instructions and markdown templates. It does not include any executable scripts, binaries, or automated code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:22 PM