monday-brief
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external, potentially untrusted sources which could contain malicious instructions.
- Ingestion points: The skill retrieves content from
~~crm,~~почта, and~~мессенджерas described in SKILL.md. - Boundary markers: There are no delimiters or specific instructions for the agent to ignore embedded commands within the processed data.
- Capability inventory: The skill is permitted to use the
Bashtool for local operations andWebFetchfor network access. - Sanitization: The instructions do not define any validation or sanitization for the ingested external content.
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to interact with the local file system. - Evidence: Step 3 of the skill instructions involves writing markdown report files to the local user path
~/Desktop/monday-brief-ГГГГ-ММ-ДД.md.
Audit Metadata