The Agent Skills Directory

[SAFE]: The skill communicates with api.leadmagic.io, which is the official API endpoint for the vendor LeadMagic. This is a legitimate and expected network operation for the skill's stated purpose.
[SAFE]: The Python script scripts/check-profile-results.py is used for offline data validation. It adheres to security best practices by using the x flag to prevent overwriting existing files and setting restrictive file permissions (0o600) so that output files are only readable by the owner.
[INDIRECT_PROMPT_INJECTION]: The skill processes bulk datasets (CSV/JSON). While this presents a surface for indirect prompt injection if data contains malicious instructions, the skill mitigates this through structured identity validation in its processing scripts.
Ingestion points: CSV uploads via POST /bulk/submit, JSON rows in batch requests, and result pages processed by scripts/check-profile-results.py.
Boundary markers: The instructions explicitly define a join contract and identity verification steps to prevent data corruption or ambiguous mapping.
Capability inventory: The skill can perform network requests to the LeadMagic API and write validated results to the local filesystem via the provided Python script.
Sanitization: The profile_identity function in the Python utility script validates and normalizes profile URL formats to ensure they match expected patterns before merging data.

bulk-jobs