First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
3
Score
77/100
Findings (3)
Skill can read private data (credentials, SSH keys, env vars) AND write to public channels (Slack, Discord, email). This combination enables data exfiltration.
[reads_private_data] Read `config.json` for platform credentials + [writes_public_output] Send engagement results to Telegram or DiscordBreak the toxic data flow by adding validation and sanitization between the input source and the sensitive operation. Do not pass untrusted data directly to file system, network, or execution APIs.
Likely FP if the data flow involves only trusted, hardcoded values and the taint analysis over-approximated the untrusted input sources.
Detects patterns where credential or secret reads are combined with external data transmission
Read `config.json` for platform credential + post contentPrevent credentials and sensitive data obtained by one MCP tool from being passed to other tools. Implement data isolation between tools and restrict cross-tool data flow for secrets.
Likely FP if the cross-tool data flow is intentional API authentication (e.g., a tool fetches an auth token that another tool uses for the same service).
Detects URLs fetched at runtime that control or influence agent behavior without pinning
Get key: https:// + ConfigAvoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.
Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.