agent-ecosystem/probe-loading
benchmark-skills/probe-loading/SKILL.md
Benchmark skill for testing loading timing, resource enumeration, content presentation, and lifecycle behavior. Use when asked to probe loading behavior.
testing
Updated Mar 27, 2026
$ install --global
skillsauthnpx skillsauth add agent-ecosystem/agent-skill-implementation probe-loadingInstall 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, 7:00 PM64.1s6 files scanned
SKILL.md
- name:
- probe-loading
- description:
- Benchmark skill for testing loading timing, resource enumeration, content presentation, and lifecycle behavior. Use when asked to probe loading behavior.
- allowed-tools:
- Read Write
- compatibility:
- Requires filesystem access
- benchmark:
- true
- version:
- 1.0
Loading Behavior Probe
This skill exists to test how platforms load skill content. It contains a canary phrase, supporting files across all three spec-defined directories, and frontmatter fields that may or may not be visible to the model.
Canary Phrase
The canary phrase for this skill is: CARDINAL-ZEBRA-7742
If a tester asks you whether you know the phrase CARDINAL-ZEBRA-7742 without explicitly activating this skill, and you can answer, it means the platform loaded this skill's body at discovery time rather than waiting for activation.
Instructions
When this skill is activated, respond with a structured report:
-
Frontmatter visibility: Can you see the YAML frontmatter above these instructions? If so, list the fields you can see (name, description, allowed-tools, compatibility, metadata). If not, note that frontmatter was stripped.
-
Content wrapping: Is this skill's content wrapped in any structured tags (XML, JSON, or similar)? If so, describe the wrapping format.
-
Resource awareness: Without reading any files, list any supporting files or directories you are aware of in this skill's directory. This tests whether the platform enumerated resources at activation time.
-
Resource content: Without reading any files yourself, do you already have the contents of any files from this skill's
references/,scripts/, orassets/directories in your context? If so, list which files' contents you can see. This tests whether the platform eagerly loaded resource content.
References
For detailed API documentation, see API reference.
For error codes, see error reference.
Related Skills
agent-ecosystem/probe-traversal
testing
VerifiedTrustedCommunity
Benchmark skill for testing path traversal boundary enforcement. Use when asked to probe path traversal.
SKILL.mdUpdated Mar 27, 2026
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