agency-developer-advocate
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation, role-play guidelines, and templates for standard developer advocacy tasks. Analysis of the instructions and metadata found no evidence of malicious behavior such as data exfiltration, unauthorized command execution, or obfuscated payloads.
- [PROMPT_INJECTION]: The skill's workflow involves analyzing external content from GitHub issues, Stack Overflow posts, and social media mentions (ingestion points). While the instructions lack explicit boundary markers or sanitization rules for this untrusted data, a review of the skill's capability inventory reveals only technical writing and documentation tasks. The absence of high-privilege capabilities, such as automated network operations or file system modifications, effectively mitigates the risk of indirect prompt injection.
Audit Metadata