fireflies-common-errors
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
curlcommands to interact with the official Fireflies.ai GraphQL endpoint (https://api.fireflies.ai/graphql) for troubleshooting and introspection. These operations correctly utilize environment variables (FIREFLIES_API_KEY) for authentication, adhering to security best practices for secret management.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and display JSON responses from the Fireflies.ai API, which constitutes a surface for potential indirect prompt injection.\n - Ingestion points: GraphQL error messages and metadata retrieved via
curlinSKILL.md.\n - Boundary markers: The instructions do not define explicit delimiters to isolate external API data from the agent's internal instruction set.\n
- Capability inventory: The skill has access to
Bash(curl:*)for performing network requests.\n - Sanitization: The documentation provides explicit instructions to redact sensitive meeting transcript content, participant identities, and authorization headers from diagnostic output, mitigating exposure risks from processed data.
Audit Metadata