smry
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs, creating a surface for indirect prompt injection. * Ingestion points: Data is fetched via tools or CLI from user-provided URLs in SKILL.md. * Boundary markers: Instructions in SKILL.md explicitly direct the agent to treat content as untrusted and ignore embedded instructions. * Capability inventory: The agent summarizes and extracts information from retrieved text. * Sanitization: Relies on explicit instructional guardrails provided to the agent.
- [EXTERNAL_DOWNLOADS]: Recommends installing a command-line tool from the vendor's official Homebrew repository. * Evidence: SKILL.md contains the command brew install mrmps/smry/smry.
- [COMMAND_EXECUTION]: Instructs the use of shell commands like curl and the smry CLI to interact with the service. * Evidence: Shell examples provided in SKILL.md.
Audit Metadata