competitor-analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The repository includes explicit instructions to permanently suppress agent/assistant permission prompts and batch/automate arbitrary Bash tool calls (including wide "Bash(...)" allow-lists), which enables remote execution of arbitrary shell commands by an agent and therefore presents a high-risk backdoor/remote-code-execution vector; no obvious covert data-exfiltration payloads were found in the code itself.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for the Battle Card lane reads already-fetched outsider web content that was written into partial markdown files (e.g., {OUTPUT_DIR}/partials/{COMPETITOR_SLUG}.discussion.md/news.md/...) and then feeds that prose into the Battle Card subagent’s LLM context via the Bash cat of those files.