email-to-tasks

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions without any executable code, scripts, or external tool invocations. It operates as a set of logical rules for text analysis and extraction.
  • [INDIRECT_PROMPT_INJECTION]: While the skill's purpose is to process untrusted external data (email threads), it lacks any capabilities (such as network access, file system writes, or command execution) that could be exploited via a malicious email. The instruction to use direct quotes from the source text acts as a manual integrity check, reducing the likelihood of the agent hallucinating or obeying instructions hidden within the analyzed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 05:56 PM
Security Audit — agent-trust-hub — email-to-tasks