social-content
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources, which could contain malicious instructions.\n
- Ingestion points: The skill reads marketing context from
.claude/product-marketing-context.md(specified inSKILL.md) and suggests analyzing large datasets of external social media posts (described inreferences/reverse-engineering.md).\n - Boundary markers: There are no instructions to use delimiters or ignore embedded instructions within the ingested content.\n
- Capability inventory: No direct tool calls, network operations, or shell commands are defined in the provided skill files.\n
- Sanitization: The instructions do not include steps to sanitize, escape, or validate the content of the ingested files or external posts.
Audit Metadata