dupcheck
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script using
uv run python3 $CLAUDE_PROJECT_DIR/tools/dedup_findings.py. This script is part of the project tools for deduplicating findings. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources.
- Ingestion points: Data fetched from external platforms via
search_hacktivityandsearch_writeupsMCP tools. - Boundary markers: No delimiters or isolation instructions are used when displaying external content to the agent.
- Capability inventory: The agent has the ability to read local files (
scope.yaml,findings.json) and execute shell commands. - Sanitization: There is no evidence of sanitization or filtering applied to the external data before it is analyzed by the agent.
Audit Metadata