spark-recipe-topic-timeline
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources such as email threads and meeting transcripts.
- Ingestion points: Data is retrieved via the
spark meetings,spark search, andspark emailscommands as defined inSKILL.md(Steps 2 and 3). - Boundary markers: The instructions do not provide delimiters or warnings to the agent to treat retrieved content as untrusted or to ignore instructions embedded within the data.
- Capability inventory: The skill uses the
sparkCLI to perform broad searches and read detailed transcript/email content. - Sanitization: There is no evidence of filtering or validation for the content retrieved from external sources before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill dynamically generates shell commands using user-provided keywords (e.g.,
spark search "topic keyword"). This interpolation of user-supplied strings into CLI execution represents a potential command injection risk if input is not properly handled by the agent or the underlying tool.
Audit Metadata