skills/iwanhe/pandawa/pm-skills/Gen Agent Trust Hub

pm-skills

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes and executes multiple Python scripts (e.g., velocity_analyzer.py, project_health_dashboard.py, jql_query_builder.py) to automate project management workflows via the command line.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources, creating an attack surface. Ingestion points: The agent reads data from Jira issues, Confluence pages, and user-provided JSON files (e.g., permissions.json, pages.json). Boundary markers: No explicit instructions are provided to the agent to treat this incoming data as untrusted or to use delimiters. Capability inventory: The skill allows the agent to execute local Python scripts and perform write/update operations in Jira and Confluence via MCP tools. Sanitization: No input sanitization or validation logic is defined for the external content processed by the analysis scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:32 PM
Security Audit — agent-trust-hub — pm-skills