Skill Discovery Abuse

6 findings 6 skills affected OWASP AST04: Insecure Metadataalso AST02

Manipulation of the name, description, or trigger metadata so the skill is selected when it should not be: keyword stuffing to hijack unrelated tasks, impersonating a well-known skill or vendor, or typosquatting a popular name.

By severity

  • MEDIUM 6

By registry

RegistryFindingsSkills affected
clawhub.ai33
jthack11
anthropic11
skills.sh11

How it shows up in a skill

Real findings from the corpus. Each links to the skill's full report.

zoho-email clawhub.ai

MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic

Detects manipulation of skill discovery to increase unwanted activation: Perfect

SKILL.md:562

python3 scripts/zoho-email.py mark-unread INBOX 1004 1005
Remediation: Review and remove skill discovery abuse pattern

simmer clawhub.ai

MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic

Detects manipulation of skill discovery to increase unwanted activation: Use this before

SKILL.md:341

### Risk Management
Remediation: Review and remove skill discovery abuse pattern

x402 clawhub.ai

MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic

Detects manipulation of skill discovery to increase unwanted activation: Perfect

SKILL.md:3

x402 enables instant stablecoin payments directly over HTTP using the 402 Payment Required status code. Perfect for AI agents paying for APIs, data, or compute on-demand.
Remediation: Review and remove skill discovery abuse pattern

ffuf-web-fuzzing jthack

MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic

Detects manipulation of skill discovery to increase unwanted activation: ALWAYS USE THIS

SKILL.md:112

# Auto-calibration - ALWAYS USE THIS
Remediation: Review and remove skill discovery abuse pattern

How to check your own skill for this

Compare the description to what the skill does. Check the author and name against the official source the skill claims to represent.

Affected skills

Name Registry Verdict SkillSpector Findings Critical High Medium Low
zoho-email clawhub.ai ISSUES FOUND Do not install 100 53 18 3 32 0
simmer clawhub.ai ISSUES FOUND Caution 33 10 2 2 3 3
x402 clawhub.ai ISSUES FOUND Caution 30 8 1 2 3 2
ffuf-web-fuzzing jthack SAFE Caution 44 5 0 0 2 3
algorithmic-art anthropic SAFE Caution 25 3 0 0 1 2
writing-skills skills.sh SAFE Do not install 100 2 0 0 1 1