senior-fullstack
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation specifies the use of local Python scripts (e.g.,
scripts/project_scaffolder.py) and standard developer tools such asnpm,docker, andkubectlfor application development and deployment tasks.\n- [EXTERNAL_DOWNLOADS]: TheSKILL.mdfile contains instructions for fetching and installing external dependencies via standard package managers (npm install,pip install).\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) due to its role in analyzing external project code.\n - Ingestion points: Target directory paths and file contents processed by the analysis tools mentioned in
SKILL.md.\n - Boundary markers: The documentation lacks explicit delimiters or instructions to ignore instructions found within analyzed files.\n
- Capability inventory: The skill has the ability to execute shell commands and scripts across its documented workflows.\n
- Sanitization: There is no evidence of input validation or content sanitization for the analyzed code.\n- [NO_CODE]: The documentation references multiple Python scripts in a
scripts/directory that were not included in the provided file set.
Audit Metadata