The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The 'Intake' procedure in SKILL.md requires the agent to ingest buyer language from win/loss reports, sales calls, and competitor teardowns. Additionally, references/playbook.md processes real deal history and case briefs.
Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings when processing these external data sources.
Capability inventory: The skill is granted high-privilege tools including bash, run_command, and write_to_file as defined in SKILL.md and agents/openai.yaml, which increases the potential impact of a successful injection.
Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is interpolated into the agent's context.

sales-enablement