developer-community-launch
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input and incorporates it into a generated document, creating a surface for potential prompt injection attacks.
- Ingestion points: User responses to the interview questions in
SKILL.mdare used to populate the Community Launch Brief. - Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore commands that may be embedded within user-provided data.
- Capability inventory: Across
SKILL.mdand all referenced files, the skill does not utilize subprocess calls, file-writing tools, or network operations, which limits the potential impact of an injection. - Sanitization: No sanitization or validation mechanisms are defined for the data ingested from the user during the workflow.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and service information from well-known platforms including GitHub, Slack, and Discourse in
references/platform-mechanics.mdandreferences/readiness-and-thresholds.md.
Audit Metadata