async-standup-compiler
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted content from external communication and tracking platforms.- Ingestion points: Slack messages, threads, and Notion/Linear tracker boards are read via connectors as described in the 'Execution' section of SKILL.md.- Boundary markers: The skill lacks explicit delimiters or instructions to wrap external content in markers that signify it should be treated as data rather than instructions.- Capability inventory: According to the 'Execution' and 'Frontmatter' sections of SKILL.md, the skill has read access to Slack, Notion, and Linear, and has the ability to post updates back to these platforms on request.- Sanitization: The instructions do not specify any sanitization, filtering, or escaping protocols for the data retrieved from external connectors before it is processed by the agent.
Audit Metadata