working-with-pm
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown instructions and references to external educational articles. No malicious patterns, obfuscation, or unauthorized data access were detected. The skill focuses on providing soft-skills advice and framework-based coaching for engineering managers.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local context files in the
.agents/directory (SKILL.md). While this represents a data ingestion surface, the skill's capabilities are limited to text generation. There are no subprocess calls, network writes, or file system modifications beyond local context updates, and no boundary markers are required for this purely instructional use case. - [EXTERNAL_DOWNLOADS]: The skill includes static links to the author's newsletter (
newsletter.manager.dev) inreferences/sources.md. These are standard documentation links for the user to follow manually and do not involve automated code execution or remote script fetching.
Audit Metadata