ClawAudit verdict
Telegram News Digest (Lite)
tg-news-digest-lite
Fetches from network AND uses eval/Function
Telegram channel monitoring skill that scrapes public t.me/s/* pages and delivers AI-generated digests; network access is limited to declared domains (t.me, OpenAI/OpenRouter), env vars are only the OpenClaw gateway token, and behavior is consistent with the stated news aggregation purpose.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (7)
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/openclaw.json
Dynamic import() — loads module at runtime
SKILL.md · code · import('
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
HTTP request to bare IP address — common in malicious payloads
src/index.js · prose · downgraded · http://127.0.0.1
Contains shortened/invite URL
SKILL.md · frontmatter · t.me/s
Popular HTTP library — network access
package.json · prose · downgraded · axios
Accesses sensitive environment variables
src/summarizer.js · prose · downgraded · process.env.OPENCLAW_GATEWAY_TOKEN
Permissions & capabilities
No declared permissions — minimal attack surface.
network_incredential_accessdynamic_evalnetwork_out Thanks — recorded.