The Agent Skills Directory

[SAFE]: No malicious patterns, direct prompt injections, or unauthorized data exfiltration were found. The skill uses environment variables for secure API key management.
[PROMPT_INJECTION]: The skill has an ingestion surface for indirect prompt injection as it processes data from external URLs, uploaded files, and user-provided text. However, the risk is minimal as the script's capabilities are restricted to API communication.
Ingestion points: materialText, materialFile, and materialUrl defined in SKILL.md and references/form-schema.json.
Boundary markers: None explicitly defined in the instructions to delimit user content.
Capability inventory: Network requests to ai-skills.ai using urllib.request in scripts/run.py.
Sanitization: No specific sanitization or escaping of external content is performed in the runner script.

ai-sales-qualification