social-content
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from a local file, which could potentially contain malicious instructions if the file's source is untrusted.
- Ingestion points: The skill reads from
.claude/product-marketing-context.mdas specified inSKILL.mdto gather marketing context. - Boundary markers: Absent. There are no instructions to treat the file content as data or to ignore embedded instructions within that file.
- Capability inventory: The skill is primarily focused on text generation for social media content. No high-risk capabilities such as subprocess execution, file writing, or network operations were detected in the provided files.
- Sanitization: Absent. There is no mention of validating or sanitizing the content retrieved from the local context file.
Audit Metadata