himalaya
Himalaya CLI for IMAP/SMTP mail: list, read, search, compose, reply, forward, copy, move, delete.
64
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This is an IMAP/SMTP email client skill whose required runtime commands can read outsider-authored email content (e.g., `himalaya message read <id>` / `envelope list`), which would be ingested by the agent/LLM as returned message text at runtime—enabling indirect prompt injection via email body/headers.
- Repository
OpenBMB/PilotDeck
- Revision
52660d5
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.