Caveat verdict

shufa-recognition

chinese-calligraphy-recognition

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Reads local files AND makes external network calls

Calls HuggingFace Inference API with image data for calligraphy font classification; sends only user-provided image content to the documented HuggingFace Space endpoint for the stated recognition purpose.

Automated static analysis โ€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

15
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence โ€” it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Reads local files AND makes external network calls โ€” the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 ยท LLM06 ยท ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Findings (2)

Pattern match high

Long base64 string (100+ chars) โ€” likely obfuscated payload

SKILL.md ยท frontmatter ยท 3046022100d61658ffc6f5bdbf4ebb1716d5aa7dca050f66263bf32e213943418ffb16c55e022100

Pattern match low

Python os.environ.get โ€” reads environment variable

scripts/recognize.py ยท prose ยท downgraded ยท os.environ.get(

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

network_outfile_read
Check another skill Browse the registry Auditing your own skills or configs? Use the API