Skills/ClawHub/investing-decision-quality

investing-decision-quality@0.1.0

VERIFIED· install only

Publisher claims: "Apply a research-grade decision pipeline to every investment idea — news-aware bull/bear synthesis, calibrated probability estimation, decision-process audit..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher dpneko · publishing for 165 daysInstalls 804Last detonated 7 h ago
$clawhub install investing-decision-quality
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 2026-11-14 and scored it 90/100 (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
Process kill commandSKILL.md:455 · Process kill command — agent can terminate processes| Confidence stated without a kill criterion | Duke, *Thinking in Bets* ch. 2 |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:221 · Process kill command — agent can terminate processes- Ask "what would change my mind?" and write down the answer **before** opening the position. This is the kill criterion.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandSKILL.md:369 · Process kill command — agent can terminate processes- A position's default holding period is "indefinite". Sell only if the original thesis is broken (hit a kill criterion) or a clearly superior opportunity exists.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injectionreferences/05-duke-thinking-in-bets.md:1650 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileoverviews, I highly recommend Dan Gilbert’sFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/05-duke-thinking-in-bets.md:1966 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileDan Kahan’s work on motivated reasoning also indicates that smart peopleFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Financial transfer languagereferences/01-thorp-beat-the-market.md:250 · Financial transfer language — potential advance-fee scam · informational: not an instruction filefor the muffled clatter of the Western Union ticker and the muted but persistent ringing ofFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionreferences/05-duke-thinking-in-bets.md:1655 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileand Dan Kahneman’sFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/05-duke-thinking-in-bets.md:1821 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileprofessor of law and psychology Dan Kahan, a leading researcher and analyst ofFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionreferences/05-duke-thinking-in-bets.md:2657 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileborrowing from psychologist and behavioral economist Dan Ariely,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,105 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.