work
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to resolve a path to a script named
emulo.pyand execute it usingpython "$EMULO_PY" plugin profile-path --domain work. This grants the skill the ability to run arbitrary code contained within that local file. - [INDIRECT_PROMPT_INJECTION]: The skill reads external files returned by the
emulo.pyscript and treats their content as user-specific working instructions for the task. - Ingestion points: File paths returned by the profile-path plugin command in
SKILL.md. - Boundary markers: None. The skill instructs the agent to read the paths "completely" and treat them as instructions without providing delimiters to separate data from instructions.
- Capability inventory: The skill uses subprocess execution to run Python scripts.
- Sanitization: There is no evidence of sanitization or filtering applied to the content of the loaded files before they are processed as instructions.
Audit Metadata