feishu-news-card
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with the
openclawCLI for message delivery. It uses platform-specific commands (caton Mac/Linux andGet-Contenton Windows) to read card JSON payloads from temporary directories.\n- [DATA_EXFILTRATION]: The skill's primary function is to transmit data to the external Feishu platform. This is a legitimate and documented egress point for its intended use case.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted news content and interpolates it into JSON structures for transmission.\n - Ingestion points: News titles, abstracts, and source links provided by users or external sources (referenced in
SKILL.md).\n - Boundary markers: None; content is placed directly into JSON fields without specific delimiters or instructions to ignore embedded commands.\n
- Capability inventory: Shell command execution via
openclawand file system writing using theWritetool.\n - Sanitization: No sanitization, validation, or escaping of input content is specified before the data is processed.
Audit Metadata