create-opportunities
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely text-based and instructional. It contains no executable scripts, shell commands, or external binary dependencies.
- [DATA_EXPOSURE]: The skill reads from local directories such as 'user-interviews/' and 'company-level-context/'. This data access is aligned with the skill's purpose and does not involve any network calls or exfiltration patterns.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass AI safety filters, override system prompts, or use role-play for malicious purposes. It maintains a consistent focus on product management tasks.
- [SAFE]: The skill processes untrusted interview data (Ingestion points: user-interviews/snapshots/). While it lacks explicit boundary markers or sanitization to isolate this data, the skill's capability inventory is limited to local text processing and file creation, with no access to dangerous tools like network requests or code execution, mitigating the risk of indirect injection.
Audit Metadata