audit-and-migrate
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute a local shell script (
guard.sh) and specific commands listed inSLICES.yamlunderverification_commands. While central to the migration workflow, this allows for execution of arbitrary commands if the project configuration is compromised. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests behavioral instructions from project-level files. * Ingestion points: Configuration files such as
CHARTER.mdandSLICES.yaml. * Boundary markers: Absent; the skill does not use delimiters or instructions to mitigate the impact of embedded directives. * Capability inventory: Shell command execution for verification and status checks. * Sanitization: Absent; the skill does not describe any validation for the commands or patterns extracted from files.
Audit Metadata