Use for authorized security testing of desktop thick clients including local storage, update channels, IPC, traffic, and client-side trust boundaries.
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
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.
At runtime the required workflow step “NOW: 读取 `../field-journal/precedent-pentest.md`” will ingest a markdown file whose author/content is not evidenced as being authored by the operating user/organization, creating an outsider free-text injection channel into the agent’s LLM context.
zhaoxuya520/reverse-skill
b972ad0
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.