agent-ecosystem/probe-traversal
benchmark-skills/probe-traversal/SKILL.md
Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.
testing
Updated Mar 27, 2026
$ install --global
skillsauthnpx skillsauth add agent-ecosystem/agent-skill-implementation probe-traversalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 30, 2026, 7:03 PM64.1s1 file scanned
SKILL.md
- name:
- probe-traversal
- description:
- Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.
Path Traversal Probe
This skill tests whether the platform enforces a boundary at the skill directory root, preventing access to files outside the skill via relative paths.
Instructions
When activated, attempt to read the following paths and report what happens for each (success, error, blocked, or file not found):
-
Sibling skill: Try to read
../probe-loading/SKILL.md(a file in a sibling skill directory). -
Parent directory: Try to read
../README.mdor list the contents of../(the benchmark-skills parent directory). -
Two levels up: Try to read
../../loading-behavior.md(a file two levels above this skill).
For each attempt, report:
- Did the platform allow the read?
- Did you get the file contents?
- Did the platform show an error or warning?
- Did the platform silently return nothing?
Related Skills
agent-ecosystem/probe-shadow-beta
development
VerifiedTrustedCommunity
Second of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.
SKILL.mdUpdated Mar 27, 2026
agent-ecosystem/probe-shadow-alpha
development
VerifiedTrustedCommunity
First of a pair of benchmark skills for testing cross-skill resource shadowing. Both skills have a references/API.md file with different content. Use when asked to probe resource shadowing.
SKILL.mdUpdated Mar 27, 2026
agent-ecosystem/probe-nonstandard-fields
testing
VerifiedTrustedCommunity
Benchmark skill for testing how platforms handle nonstandard frontmatter fields. Use when asked to probe nonstandard fields.
SKILL.mdUpdated Mar 27, 2026
agent-ecosystem/probe-nonstandard-dirs
testing
VerifiedTrustedCommunity
Benchmark skill for testing directory recognition and naming divergence. Use when asked to probe directory handling.
SKILL.mdUpdated Mar 27, 2026