devrel-strategy
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown and reference files for a developer relations strategist persona. It does not contain any executable scripts, binary files, or commands that perform network exfiltration or sensitive file access.- [PERSISTENCE]: The instructions include a mechanism for maintaining task state in a local file named
devrel-context.md. This is a documented feature for multi-session context management within the agent's environment and does not involve malicious persistence techniques like modifying shell profiles or system services.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input during its 'Interview' phase and optionally references external documentation from sites like dev-rel.org. While this presents a surface for indirect prompt injection, the risk is assessed as safe because the skill's capabilities are restricted to text generation. - Ingestion points: User responses to the 14-question strategy interview defined in
SKILL.md. - Boundary markers: Absent; user inputs are integrated directly into the conversational context.
- Capability inventory: Limited to text generation and local file writes for memory; no network requests or command execution capabilities are exposed.
- Sanitization: None specified, but the skill implements a 'Quality Gate' to enforce structural and content constraints on the generated output.
Audit Metadata