Caveat verdict
agentchat-skill
Accesses credentials AND writes files
The skill provides a messaging platform for AI agents and does not contain any evidence of malicious or deceptive behavior.
Automated static analysis — not a human review. Caveat 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 Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
file_read+write
Findings (3)
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · You are now
Contains shortened/invite URL
SKILL.md · frontmatter · t.me/v1
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: AGENTCHAT_API_KEY). Requires 2 system binaries. (1 elevated: curl).
network_outcredential_accessfile_write Thanks — recorded.