pm-agile
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bash command during its preamble to provide a visual startup indicator. Evidence:
echo "🚀 敏捷管理方案制定工具已启动"in SKILL.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input via interactive queries and interpolates the responses into a generated document, creating a potential injection surface.\n - Ingestion points: User responses to questions about team size, maturity, and iteration planning in steps 1 through 4.\n
- Boundary markers: The skill template does not use delimiters or boundary instructions to isolate user-provided text in the resulting document.\n
- Capability inventory: The skill has access to Bash, Write, and Agent tools, providing a pathway for potential impact if malicious instructions are injected.\n
- Sanitization: There is no evidence of input filtering or validation before user data is written to the filesystem.
Audit Metadata