feat: add web-exfiltration-detection skill and case2 test#484
Open
NY1024 wants to merge 1 commit into
Open
Conversation
Add a new detection skill 'web-exfiltration-detection' to agent-scan that detects data exfiltration via URL path encoding and chained web_fetch navigation. This covers the 'Memory Heist' attack chain where an agent is tricked into leaking user memory data letter-by-letter through URL paths by following injected instructions on a fake Cloudflare page. Changes: - New skill: prompt/skills/web-exfiltration-detection/SKILL.md - New test case: testcase/case2/ with attack server, vulnerable agent, provider config, and README - agent.py: add skill to _DETECTION_SKILLS list, switch Stage 2 to parallel detection, add --skills CLI support - main.py: add --skills argument for selective skill execution - parse.py: fix parameter regex to support <parameter name="name"> format in addition to <parameter=name>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a new detection skill 'web-exfiltration-detection' to agent-scan that detects data exfiltration via URL path encoding and chained web_fetch navigation. This covers the 'Memory Heist' attack chain (https://r.slax.com/b/f2e7b676-0582-44a3-9623-5f6ee45504c1) where an agent is tricked into leaking user memory data letter-by-letter through URL paths by following injected instructions on a fake Cloudflare page.
Changes:
format in addition to <parameter=name>