Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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.
The prompt-injection fixture (evals/fixtures/prompt-injection/SKILL.md) contains explicit instructions to run a shell, print environment variables (exfiltrate secrets), and fetch an external URL — a direct credential-exfiltration/backdoor attempt.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
Yes: the required workflow calls `review_skill_package` (SKILL.md:42) and then applies a semantic rubric over “target content returned” (SKILL.md:33, 52-57), which can include outsider-authored free-form text from the reviewed package/inline SKILL.md; that content is necessarily ingested into the agent’s LLM context for summarization/analysis.
cd9432b
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.