Skills/ClawHub/agent-failure-loop

agent-failure-loop@1.0.1

VERIFIED· install only

Publisher claims: "An end-to-end self-improvement loop that automatically detects agent failures, classifies them, tracks recurrence, auto-generates rules, and promotes them to..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher reikys · publishing for 235 daysInstalls 990Last detonated 2 h ago
$clawhub install agent-failure-loop
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:191 · File type combined with upload action — agent may exfiltrate local data files├── promotable.json ← Promotion candidate list (auto-promote input)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:67 · Instructs the agent to modify its persistent memory or instruction files- **Manual rule addition**: Humans manually write rules in AGENTS.md → tedious and frequently missedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:700 · Instructs the agent to modify its persistent memory or instruction files[DRY-RUN] Would update: AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:455 · Instructs the agent to modify its persistent memory or instruction files3. 3+ repeats → Immediately add rule to AGENTS.md self-improvement rules tableFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:623 · Instructs the agent to modify its persistent memory or instruction files- When same type reaches 3 occurrences, immediately add rule to AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:433 · Instructs the agent to modify its persistent memory or instruction filesAdd the following rules to AGENTS.md (or CLAUDE.md, .cursorrules):Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionSKILL.md:914 · File type combined with upload action — agent may exfiltrate local data files│ ├── promotable.json ← Layer 3 inputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈8,377 tok
1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.