skills/rohitg00/auto-claude-code-research-in-sleep/comm-lit-review-claude-single/Gen Agent Trust Hub
comm-lit-review-claude-single
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the
$ARGUMENTSvariable. - Ingestion points: User-provided research topics enter the agent context via the
$ARGUMENTSplaceholder inSKILL.md. - Boundary markers: There are no delimiters (e.g., XML tags, triple quotes) or explicit instructions to ignore embedded commands within the research topic input.
- Capability inventory: The skill possesses significant capabilities, including local file system access (
Read,Glob,Grep,Bash), web access (WebSearch,WebFetch), and access to personal data via Zotero and Obsidian MCP tools. - Sanitization: There is no evidence of input validation or escaping for the user-supplied arguments before they are processed by the agent.
Audit Metadata