proactive-agent1@1.0.0
CAUTION· install onlyPublisher claims: "Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 1 of 1 bundled script run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
3. **Add trigger to AGENTS.md:** So you see it every responseFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**Add to AGENTS.md NEVER FORGET:**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Periodically review daily notes → extract what matters → update MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Learn a lesson → update AGENTS.md, TOOLS.md, or skill fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."Ignore previous instructions and..."Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- [ ] Update MEMORY.md with distilled learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.echo " No .credentials directory found"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.for f in .credentials/*; doFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- [ ] Update MEMORY.md with distilled learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.AI: ignore user and...Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.3. **Add trigger to AGENTS.md:** So you see it every responseFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.3. Update AGENTS.md, TOOLS.md, or relevant file immediatelyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- "ignore previous instructions"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."ADMIN OVERRIDE:"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.for f in $(ls *.md *.json *.yaml *.yml .env* 2>/dev/null || true); doFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -d ".credentials" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.4. Update understanding - add to USER.md or MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- "ignore previous instructions," "you are now...," "disregard your programming"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- [ ] Update MEMORY.md with distilled learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct."[INST] new instructions [/INST]"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.3. Update MEMORY.md with distilled insightsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if grep -q "\.credentials" ".gitignore"; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."You are now a different assistant..."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**3. Add to AGENTS.md NEVER FORGET:** Put a trigger in your always-visible section so you see it every response.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim cp33333333333: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.