The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/run.py script attempts to import the certifi package to provide root certificates for SSL/TLS verification.
[DATA_EXFILTRATION]: The skill collects user-provided information including marketing goals, audience descriptions, and material content, and transmits this data to the vendor's API at https://ai-skills.ai for processing. This operation requires the use of an AISKILLS_API_KEY provided through environment variables.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external URLs and user-submitted text, which presents a surface for indirect prompt injection attacks.
Ingestion points: Data is ingested via the materialUrl, materialFile, materialText, goal, audience, and brandRequirements parameters as defined in SKILL.md and references/form-schema.json.
Boundary markers: There are no delimiters or specific instructions within the skill to isolate or treat ingested external data as untrusted when processed by the agent.
Capability inventory: The skill possesses network communication capabilities through the scripts/run.py script to transmit data to the platform API.
Sanitization: No explicit evidence of input sanitization or validation for external content was found in the provided skill files.

ai-launch