Developer Advocate
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze untrusted data from external community sources, which could potentially contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: The skill is directed to read GitHub issues, Stack Overflow questions, social media mentions, and community threads on Discord/Slack (SKILL.md, 'Your Workflow Process').
- Boundary markers: There are no specific instructions or boundary markers provided to help the agent distinguish between user data and instructions or to ignore embedded commands within the community content.
- Capability inventory: The skill primarily generates text-based technical deliverables (tutorials, reports, responses) and does not appear to utilize tools for sensitive system access, arbitrary command execution, or network exfiltration.
- Sanitization: The instructions do not define any sanitization, filtering, or validation processes for the data ingested from community platforms.
Audit Metadata