Score-based assessment (high risk, 80/100). An AI review is available in the AI review tab.
Analysis record
- Analysed
- 2 weeks ago 1 November 2026
- Version
- vb0c6f8030535
- Artifact
- SHA256 17f5a320…ca046d
- Detail
- Full list
Evidence ledger
Ranked by severity · findings with a source location link to the code viewer
YARA Rule Matches
11 rules| Severity | Rule | Hits | Files | Metadata |
|---|---|---|---|---|
| LOW | postinstall network communication | 35 | skills/magpie-kernel-evaluator/SKILL.mdskills/lemonade-router-builder/SKILL.mdskills/lemonade-router-builder/examples.md +32 more | - |
| LOW | postinstall system command | 100 | walkthroughs/lemonade-router-builder.mdskills/magpie-kernel-evaluator/evals/evals.jsonskills/tracelens-analysis-orchestrator/agents/convolution-analyzer.md +97 more | - |
| LOW | UsingShellInterpreterWhenExecutingOSCommands | 1 | skills/local-ai-app-integration/reference.md | - |
| LOW | postinstall obfuscation | 68 | skills/magpie-kernel-evaluator/examples.mddocs/skill-requirements.mdeval/claude_eval.py +65 more | - |
| LOW | postinstall crypto operations | 2 | skills/serving-llms-on-instinct/data/recipes_cache.jsonskills/local-ai-app-integration/reference.md | - |
| LOW | postinstall file manipulation | 49 | .github/scripts/sources.yml.github/workflows/label-skill-issues.ymlskills/tracelens-analysis-orchestrator/evals/hooks.py +46 more | - |
| LOW | postinstall registry modification | 10 | staging/apu-memory-tuner/scripts/detect_platform.pystaging/apu-memory-tuner/scripts/apply_profile.pyskills/serving-llms-on-epyc/reference.md +7 more | - |
| LOW | postinstall file download | 36 | .github/skillspector-allow.ymlskills/local-ai-app-integration/SKILL.mdskills/serving-llms-on-instinct/scripts/sync_recipes.py +33 more | - |
| LOW | credential env files | 28 | skills/local-ai-app-integration/SKILL.mdskills/local-ai-app-integration/reference.mdskills/hyperloom-workload-optimizer/scripts/launch.sh +25 more | - |
| LOW | postinstall persistence mechanism | 14 | skills/hyperloom-workload-optimizer/SKILL.mdskills/serving-llms-on-instinct/data/recipes_cache.jsonskills/hyperloom-workload-optimizer/scripts/tests/test_launch_flow.sh +11 more | - |
| LOW | package json suspicious scripts | 1 | skills/serving-llms-on-instinct/data/recipes_cache.json | - |
Network Indicators
Concrete URLs, domains, IPs, emails, and hashes extracted from the analyzed artifact.
Loading network indicators
Long lists can take a few seconds.
Finding Categories
YARA Rules Matched
11 rules(344 hits)AI Security Report
AI Security Review
Evidence context: threat category tool poisoning; evidence quality moderate.
Jev rated 8 findings against the supplied code: 1 likely real, 3 likely benign pattern matches. Likely real: SKILL-PROMPT-INJECTION-skills/local-ai-use/SKILL.md-6 (skills/local-ai-use/SKILL.md:6). The finding list was truncated; findings beyond it were not rated.
Key Reasons
- SKILL-PROMPT-INJECTION-skills/local-ai-use/SKILL.md-6 (skills/local-ai-use/SKILL.md:6)
- SKILL-EXCESSIVE-AGENCY-staging/rocm-doctor/SKILL.md-84 (staging/rocm-doctor/SKILL.md:84)
- SKILL-PROMPT-INJECTION-skills/local-ai-use/SKILL.md-305 (skills/local-ai-use/SKILL.md:305)
False Positive Considerations
- YARA--credential_env_files (.github/skillspector-allow.yml)
- YARA--postinstall_obfuscation (.github/skillspector-allow.yml)
- YARA--postinstall_persistence_mechanism (.github/lychee.toml)
Reviewed 2026-11-15 · version b0c6f8030535; recommended action: escalate; model confidence 52%.
Source Code Not Available
Source code is not available for this version of the extension.
About This Extension
Frequently Asked Questions
Similar Extensions
Related extensions from the same publisher or marketplace