buildcast
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external social media platforms to generate content and draft replies.
- Ingestion points: The skill fetches post text from external social media URLs as described in
references/operations.mdunder the "Reply engine" section, and mines local project documentation (git logs, changelogs, issues) as described in the "Ideation" section. - Boundary markers: Content is placed within structured Markdown templates (defined in
assets/templates/post-template.md), but lacks explicit instructions for the agent to ignore embedded instructions in the ingested text. - Capability inventory: The skill possesses file-write capabilities in the local repository and network-read capabilities to fetch external post data.
- Sanitization: There is no evidence of sanitization or filtering for the external text before it is used for drafting or ideation.
Audit Metadata