The Agent Skills Directory

[SAFE]: The skill is a legitimate engineering tool designed for internal support workflows, with all resources and references pointing to SpotDraft's official infrastructure.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it retrieves and processes content from external communication and tracking tools.
Ingestion points: External data enters the context via slack_read_thread, slack_read_channel, slack_search_public, and searchJiraIssuesUsingJql in the SKILL.md file.
Boundary markers: No specific delimiters or "ignore instructions" wrappers are used for the data ingested from Slack or Jira.
Capability inventory: The skill utilizes the execute_sql tool for BigQuery, allowing the agent to query database tables based on investigation results.
Sanitization: There is no evidence of sanitization or strict schema validation for content retrieved from external sources before it is processed by the agent.
[COMMAND_EXECUTION]: The skill provides a structured Python script template intended for manual execution by an engineer within a Django shell. While this provides a mechanism for data modification, it is documented as a remediation step and utilizes standard application service methods.

tpp-workflow-stale-entity-mapping