replacement-governance
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
check-governance.pyandupdate-manifest.py) to automate governance validation and update project state based on provided configurations.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a process where external data from JSON files drives the logic for shell command execution, creating a surface for indirect injection.\n - Ingestion points: The agent is instructed to read
.replacement/manifest.jsonand.replacement/governance.jsonto determine system scope, ownership, and approval status.\n - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within these JSON fields.\n
- Capability inventory: The skill has the capability to execute shell commands and modify local repository metadata via script execution.\n
- Sanitization: The
check-governance.pyscript performs structural validation (checking for required keys and date formats) but does not sanitize or escape the content of the string fields before they are used in the workflow.
Audit Metadata