matrix-communication

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes an explicit example of passing a recovery key on the command line (--recovery-key "EsTj ...") which instructs embedding a secret value verbatim in generated commands, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads user-generated Matrix room content (e.g., scripts like scripts/matrix-read-e2ee.py and matrix-fetch-keys.py, plus SKILL.md/README and references/messaging-guide.md) — including instructions to use --json output and jq to analyze messages and reactions — so untrusted third‑party messages from Matrix rooms are ingested and can influence programmatic decisions and follow-up actions.