The Agent Skills Directory

[SAFE]: The skill's primary function is microcopy management and naming consistency. The logic is implemented through standard Python scripts and Markdown workflows with no evidence of malicious intent or hidden behaviors.
[DATA_EXPOSURE]: The profile management script (scripts/profile_store.py) implements a proactive security measure by maintaining a list of sensitive keywords (token, secret, password, credential, cookie, api_key, apikey) and explicitly blocking any attempt to persist values associated with these keys.
[COMMAND_EXECUTION]: Deterministic detectors flagged subprocess.run in tests/test_audit_names.py. Analysis confirms this is a benign usage within a unit test suite to execute the skill's own audit script (scripts/audit_names.py) using the current Python executable (sys.executable) on temporary test data.
[OBFUSCATION]: The naming audit utility (scripts/audit_names.py) uses Unicode NFKC normalization and case-folding during string comparisons. This is a security best practice to prevent homoglyph attacks or spoofing of skill names using confusable characters.
[EXTERNAL_DOWNLOADS]: The skill does not perform runtime network requests. External dependencies are limited to standard libraries and PyYAML for local configuration parsing.

lov-skill-namer