The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external, potentially untrusted data from account lists (e.g., outputs from lead-scoring or agency-signal-sourcer). This creates a surface where malicious instructions could be embedded within fields like company names or signal descriptions to influence the agent's behavior or the content of the generated dossiers.
Ingestion points: The skill reads structured lists containing company names, signals, and roles from external tool outputs or files.
Boundary markers: Absent. The instructions do not define specific delimiters or "ignore" commands for the content within the ingested fields.
Capability inventory: The skill instructs the agent to read external data and perform file-system write operations (creating output/prospect-profiles.csv). It does not appear to have network access or arbitrary code execution capabilities.
Sanitization: Absent. There are no instructions to sanitize or escape the incoming lead data before processing it into the final dossiers.

prospect-profiler