The Agent Skills Directory

[SAFE]: The skill's primary function is to provide guidance and local linting tools for conversational advertising. A thorough review of the provided scripts and markdown files reveals no malicious intent or security risks.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The scripts scripts/conversational_ad_planner.py and scripts/answer_adjacent_copy_linter.py rely entirely on Python's standard library and do not invoke external compilers, package managers, or remote shells.
[DATA_EXFILTRATION]: There are no network-capable operations (like curl, requests, or socket) present in the scripts. Data processing is confined to local JSON inputs and standard output.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided data (ad copy and marketing briefs), it does not have the capability to act on malicious instructions within that data.
Ingestion points: scripts/conversational_ad_planner.py (brief JSON) and scripts/answer_adjacent_copy_linter.py (ads JSON).
Boundary markers: Uses structured JSON for data ingestion.
Capability inventory: No subprocess calls, file-write operations, or network requests are present.
Sanitization: Not applicable as the scripts only produce text reports.
[CREDENTIALS_SAFE]: No hardcoded API keys, tokens, or private secrets were found. The skill correctly recommends using standard UTM parameters and platform macros for tracking.

conversational-ads