task-progress
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
mc mirrorandhermes-synctools to synchronize task-related files and state with a storage backend. - [DATA_EXFILTRATION]: Content within the local
~/shared/tasks/directory is uploaded to a remote destination specified by theAGENTTEAMS_STORAGE_PREFIXenvironment variable. - [PROMPT_INJECTION]: The skill contains a vulnerability to indirect prompt injection during its task resumption flow. \n
- Ingestion points: The agent is instructed to read contents from
spec.md,plan.md, and progress log files in the task directory. \n - Boundary markers: The instructions do not define any delimiters or safety markers to isolate potentially untrusted content in these files. \n
- Capability inventory: The agent has access to the local file system and the ability to execute shell commands (
mc mirror). \n - Sanitization: There is no mechanism described for validating or sanitizing the content of the task files before they are processed by the agent.
Audit Metadata