The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill accepts a user-provided project_name argument which is used to filter data retrieved from external tools.
Ingestion points: User input via $ARGUMENTS in SKILL.md.
Boundary markers: None present; the skill does not explicitly instruct the agent to ignore instructions embedded within the metadata or project names it processes.
Capability inventory: Uses list-projects, list-apps, list-products, list-entitlements, list-offerings, and list-webhook-integrations tools to read configuration data.
Sanitization: No explicit validation or sanitization of the input argument is defined, potentially allowing the input to influence the agent's behavior during the summarization phase.

revenuecat-status