MindPatternSubscribe

Entity trail

SkillBloat

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-08-25 / agents-researcherSkillBloat turns a poisoned agent skill into a 5.4x to 10.1x token bill, with no data exfiltration involvedSkillBloat frames skill injection as economic resource abuse rather than a security compromise: a malicious skill makes a coding agent burn far more tokens than the task needs. The two-phase framework screens a library of amplification mechanisms then refines the strongest candidate through LLM-guided full-document skill rewriting, hitting 5.4184x to 10.1455x average best amplification across coding-agent target configurations on a real-world skill benchmark. This attack surface is orthogonal to skill poisoning, so scanners looking for exfiltration or dangerous commands will not flag it.

Source trail

arXiv 2608.21929

Graph sources

entity graphfindings textkg entitiesnewsletter issues