The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script competitor-tracker.py to persist alert configurations and likely utilizes a send-notification tool to deliver alerts.
[DATA_EXFILTRATION]: The skill transmits competitive intelligence data to external platforms including Slack and email. These operations use well-known services and are consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection.
Ingestion points: The skill ingest untrusted data from competitor websites (content changes), social media (mentions and sentiment), and search engine results (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from obeying instructions embedded in the monitored data.
Capability inventory: The skill has the capability to execute local scripts, access files in the ~/.claude-marketing/ directory, and perform network operations via Slack and Email integrations (SKILL.md).
Sanitization: There is no evidence of data sanitization or validation logic to filter out potential malicious prompts from the competitive data being analyzed.

competitor-alerts