The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external call transcripts (e.g., from Fathom) and client performance metrics to generate reports and outreach messages.
Ingestion points: Transcripts are processed in references/qbr.md and metrics/transcripts are processed in references/value-note.md.
Boundary markers: The instructions do not specify any boundary markers (such as XML tags or specific delimiters) to isolate untrusted transcript data from the agent's internal reasoning.
Capability inventory: The skill has access to powerful tools including bash, run_command, and write_to_file, as defined in the SKILL.md frontmatter and agents/openai.yaml configuration.
Sanitization: There is no evidence of sanitization or validation logic to filter out potentially malicious instructions embedded within the ingested transcripts before they are processed by the agent.

retain