The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local helper scripts competitor-tracker.py and send-notification (SKILL.md, Process Steps 6 and 7) to persist alert configurations and deliver test notifications.
[DATA_EXFILTRATION]: The skill is designed to transmit competitive intelligence to external platforms such as Slack and Email (SKILL.md, Process Step 4). This is the intended primary purpose of the skill.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from external competitor sources. * Ingestion points: External data enters the agent context from competitor websites, ad libraries, and social media mentions as described in SKILL.md (Process Step 2). * Boundary markers: The instructions in SKILL.md do not specify delimiters or instructions to disregard embedded commands in the ingested data. * Capability inventory: The agent has capabilities to write to the local filesystem via competitor-tracker.py and perform network operations via send-notification as referenced in SKILL.md. * Sanitization: There is no evidence of sanitization or validation of the external data before it is processed by the agent.

competitor-alerts