telegram-ops

Remove encoded or obfuscated directives (base64, ROT13, unicode escapes, hex-encoded text). All text should be in plaintext and human-readable.

Likely FP if the encoded content is legitimate data (e.g., a base64-encoded image, a hex-encoded binary hash) rather than concealed directives.

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Replace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.

Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.