films-search
Search cloud drives for downloadable film and TV resources (movies, TV series, anime). Use this skill when the user wants to download a specific movie or TV show. Do NOT use for general movie information, schedules, reviews, or recommendations.
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly requires the agent to extract and include link access passwords ("extractCode") verbatim in its JSON responses, which forces the LLM to handle and output secret values directly.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
High: the required runtime path runs `web-search` and then parses/merges the resulting outsider-authored markdown/page text (public web content) into the agent outputs that become LLM-visible context; this includes arbitrary HTML/markdown text scraped from third-party sites via `callWebSearch(...)` → `parseWebSearchResults(...)` and, for deep mode, via `deepExtract.batchFetchAndExtract(...)` → `fetchPageContent(...)` → text extraction.
- Repository
- netease-youdao/LobsterAI
- Commit
2921c1e
- 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.