project-manager
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- [SAFE] (SAFE): Analysis of the provided SKILL.md file revealed no indicators of prompt injection, data exfiltration, obfuscation, or malicious command execution. The skill content is restricted to documentation templates and local data processing logic for project management tasks.\n- [Indirect Prompt Injection] (INFO): The skill identifies ingestion points for untrusted data (YAML/CSV files) processed by local Python scripts. This constitutes a theoretical attack surface, though the identified capabilities are limited to reporting and visualization.\n
- Ingestion points:
wbs.yaml,risks.csv,team.yaml, andtasks.csv(referenced in SKILL.md).\n - Boundary markers: Absent in provided markdown templates.\n
- Capability inventory: Subprocess execution of local Python scripts (
timeline_gen.py,risk_analyzer.py,status_report.py,resource_plan.py) for project data processing.\n - Sanitization: Unverifiable as script source code is not included in the provided file.
Audit Metadata