The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from social media and web searches to score leads and draft outreach. This creates a surface where maliciously crafted external profiles or posts could influence the agent's behavior.
Ingestion points: signal-scorer.md and enrichment-agent.md fetch content from Exa, X API, GitHub, and general web URLs.
Boundary markers: Absent; the agent instructions do not include specific delimiters or warnings to ignore instructions embedded in the fetched data.
Capability inventory: The agents have access to Bash (in signal-scorer.md, enrichment-agent.md, and mutual-mapper.md), WebSearch, WebFetch, and integrations for Apple Mail and browser automation mentioned in SKILL.md.
Sanitization: No explicit sanitization, validation, or escaping of the external content is required in the agent prompts.

lead-intelligence