Capability drift in tigu77/tiguclaw

github tigu77/tiguclaw D

Always-on, self-hosted AI agent runtime — multi-LLM, parallel sub-agents, Telegram/Web/CLI, skills, memory, MCP.

maintainer: tigu77
tools: 9
CVEs: 0
releases: 126

advisory #768883

HIGH tigu77/tiguclaw 08-21 02:46

code analysis flagged committed secret in tigu77/tiguclaw

current permission surface (inferred):

drift timeline for tigu77/tiguclaw → security tab →

drift history for this server newest 8

HIGH 09-07 16:10 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-06 12:43 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-05 10:45 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-04 11:44 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-03 06:58 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-02 00:31 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-01 12:42 code analysis flagged committed secret ×3 in tigu77/tiguclaw
HIGH 09-01 11:42 code analysis flagged committed secret ×3 in tigu77/tiguclaw

Each entry is one capability capture differing from the one before it — a review signal, not a verdict.