repo-engine
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The test script
tests/run-validation.pyutilizessubprocess.runto execute a local companion script (scripts/validate-output.py) for automated validation of the skill's output format. The execution is handled securely by passing arguments as a list (avoiding shell injection) and using the system's own Python interpreter viasys.executableto run local files with hardcoded relative paths. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and process untrusted repository data via the
read_filetool to generate onboarding artifacts. - Ingestion points: Files within the repository being scanned (referenced in
SKILL.mdandreferences/workflow.md). - Boundary markers: The skill lacks explicit prompt-level delimiters for external data, though it enforces structure through the
references/artifact-schema.mdand validation scripts. - Capability inventory: The skill is limited to
list_dirandread_fileas defined in theallowed-toolsfrontmatter inSKILL.md. It possesses no write, network, or arbitrary command execution capabilities in its primary operational loop. - Sanitization: Output format validation is performed by
scripts/validate-output.pyto ensure compliance with the repository mapping schema, andtests/validation-checklist.mdinstructs the agent to ground all findings in actual file evidence rather than assumptions.
Audit Metadata