pstack-skill
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes scripts to fetch updates from official GitHub repositories and uses package managers to install well-known libraries for its statechart generation tool. These operations target well-known domains and are part of the skill's maintenance and tooling requirements.
- [COMMAND_EXECUTION]: Extensive use of shell commands and CLI tools like git and gh is present to automate engineering workflows such as PR management and version control. These are legitimate operations for a development-focused skill.
- [INDIRECT_PROMPT_INJECTION]: The skill's workflows ingest untrusted data from GitHub PR review comments and descriptions. It contains explicit instructions and warning markers for the agent to treat this data as untrusted and prioritize empirical evidence over external claims.
- [DYNAMIC_EXECUTION]: The skill employs local scripts to automate specialized engineering tasks like validating plans and generating statecharts. These scripts are part of the skill's bundled logic and do not execute arbitrary untrusted code.
Audit Metadata