knowledge-synthesis
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (research evidence and templates) which presents an attack surface for indirect prompt injection.
- Ingestion points: Reads research evidence and source files from
.claude/tmp/and report templates from.claude/templates/(SKILL.md). - Boundary markers: Absent; external content from files is interpolated directly into the synthesis process without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill utilizes
Bash,Write, andEdittools, which could be leveraged to execute commands or modify files if malicious instructions are present in the ingested research data. - Sanitization: No explicit validation, escaping, or sanitization steps are defined for the content loaded from external files.
Audit Metadata