emoji and tg stickers use proactively based on mood

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: tg-sticker-emoji-mood Version: 3.0.0 The skill bundle is classified as suspicious due to a critical shell injection vulnerability (specifically, Python code injection) found in `scripts/send_sticker.sh`. The `emoji` parameter, when passed to the `send_sticker_by_emoji` function, is directly embedded into a `python3 -c` command string without proper sanitization. This allows an attacker to break out of the Python string literal using a single quote and execute arbitrary Python code, leading to potential Remote Code Execution (RCE) on the host system. While the `SKILL.md` instructions are benign and align with the stated purpose, they direct the AI agent to use this vulnerable script.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The bot could send stickers into private or group chats more often than the user expects, creating spam, awkward posts, or inappropriate public-facing reactions.

Why it was flagged

The skill explicitly encourages frequent autonomous posting into Telegram chats without per-message approval or clear chat/rate scoping.

Skill content
You have the ability to send Telegram stickers and emojis **on your own** ... do NOT need the user to ask ... Send a sticker **before** your text reply — roughly **80–100% of the time**
Recommendation

Add explicit opt-in per chat, rate limits/cooldowns, and confirmation or stricter rules for group, channel, formal, or business-critical conversations.

ConcernMedium Confidence
ASI05: Unexpected Code Execution
What this means

If an attacker can influence the emoji argument through the conversation or prompt injection, the helper may run arbitrary code in the agent's local environment.

Why it was flagged

The shell argument is embedded directly into a Python -c program. A crafted emoji value containing quotes/Python syntax could execute unintended Python code if the agent passes it through.

Skill content
--emoji)      EMOJI="$2";      shift 2 ;; ... emoji = '${emoji}'
Recommendation

Do not interpolate arguments into code strings. Pass the emoji via stdin, environment, or JSON, validate it as an expected emoji value, or safely quote it with a proper serialization method.

What this means

Anyone with the bot token could control the bot’s API actions, including sending messages or stickers where the bot has access.

Why it was flagged

The Telegram bot token is used to call the Telegram Bot API and send stickers, which is expected for the stated purpose but still grants account/bot authority.

Skill content
Requires: TELEGRAM_BOT_TOKEN environment variable ... API="https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}" ... /sendSticker
Recommendation

Use a dedicated bot token, keep it only in a secure environment variable, restrict the bot’s chat permissions where possible, and rotate the token if it may have been exposed.

What this means

Version or provenance inconsistencies can make it harder to verify exactly which package was reviewed or installed.

Why it was flagged

The registry metadata lists version 3.0.0, while the packaged _meta.json lists 2.0.0; combined with unknown source/homepage metadata, this is a minor provenance/reviewability gap.

Skill content
"version": "2.0.0"
Recommendation

Publish consistent package metadata and provide a source/homepage link or other provenance information; users should review the included files before enabling the skill.