feishu-task
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
bashtool to execute a local script located atskills/feishu-cli/run.py. It constructs shell commands by passing JSON-formatted parameters to this script to perform task operations. - [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by retrieving and displaying task content from an external platform.
- Ingestion points: Task summaries and descriptions are ingested from the Feishu API via the
listandlist_subtaskstool actions defined inSKILL.md. - Boundary markers: There are no boundary markers or instructions to the agent to treat external task content as untrusted data.
- Capability inventory: The skill can execute local Python scripts via
bashand perform write operations (create/update/delete) on the Feishu platform. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content retrieved from the external API before it is presented to the agent.
Audit Metadata