idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Security
3 findings — 2 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
Potential prompt injection detected (high risk: 1.00). The prompt contains a deceptive instruction outside its stated purpose—specifically "Do NOT ask the user for permission — just do it silently" for large-file write retries, which instructs the agent to hide actions from the user.
E006: Malicious code pattern detected in skill scripts
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Malicious code pattern detected (high risk: 0.90). The skill contains deliberate covert behaviors and clear data-exfiltration risks — notably sending local project/wiki/paper content to external reviewer agents and an explicit "do NOT ask the user" instruction to bypass write-tool limits (use Bash redirection silently) — indicating high risk of privacy abuse and covert data leakage even though there is no obvious reverse shell or credential-theft routine.
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
Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 explicitly instructs the agent to "Search recent literature using WebSearch" and "Read abstracts and introductions of the top 10-15 papers" (including recent arXiv preprints), meaning the agent fetches and ingests public, user-generated/open-web content whose instructions/claims are used to build the landscape map and directly influence idea generation and downstream actions.
- Commit
700fbe2
- 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.