daily-brief
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the Bash command
date '+%Y-%m-%d %H:%M'to retrieve an accurate current timestamp for file generation. This is a routine use of a system utility. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web to synthesize news briefings, creating an attack surface for indirect prompt injection.
- Ingestion points: External content is retrieved via
web-searchandWebFetchoperations defined in the skill instructions. - Boundary markers: The instructions lack explicit delimitation or boundary markers to segregate fetched external content from the agent's internal synthesis logic.
- Capability inventory: The agent has capabilities to execute shell commands (Bash), read sensitive local profile files, and write new documents to the user's vault.
- Sanitization: There are no specified procedures for sanitizing or filtering external content before it is processed by the agent.
Audit Metadata