referral-program

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from local files (.agents/product-marketing-context.md or .claude/product-marketing-context.md) to gather project-specific context. This ingestion creates a surface for indirect prompt injection where an attacker who can modify these local files could influence the agent's behavior.
  • Ingestion points: The skill specifically reads local context files in the project directory as described in SKILL.md.
  • Boundary markers: Absent; the skill does not specify any delimiters or instructions to ignore embedded commands within the ingested context.
  • Capability inventory: No code execution (subprocess, eval, exec), file writing, or network capabilities are present in the provided files.
  • Sanitization: Absent; the instructions do not include steps for validation, escaping, or filtering of the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:46 AM