Versioned security assessment

Report ID: SA-C43861A6

7/23/2026, 12:11:13 PM

self-improving-agent security assessment v8

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
self-improving-agent
Version
v8
Maintainer
charon-fan
Source
github.com/charon-fan/agent-playbook/tree/main/skills/self-improving-agent/
Coverage
10 Files scanned · 1,091 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

Medium

1 confirmed security finding requires attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Static findings are predominantly false positives caused by Markdown code fences, inline backticks, research links, and documentation of local paths. The bundled hook scripts only log event metadata and output lengths; they do not perform network requests, command interpolation, or memory writes. The documented automatic memory workflow still needs privacy controls because it can retain context from many skill events.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

Audit attestation

Active attestation

A public attestation is available for this exact report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

10 Files scanned · 1,091 Lines analyzed

1 item shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 12 evidence locations

Filesystem access

May read or write local files.

Observed in 2 evidence locations

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 48 evidence locations

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:33-39SKILL.md:80-86README.md:20-29
Automatic cross-skill memory collection may retain sensitive task context
The skill describes automatic capture of experiences from all skill events and memory artifacts, but does not define data minimization, retention, or consent controls. Users may record task details or tool-related context in a persistent local memory store.
The documentation explicitly states universal event learning and identifies persistent semantic, episodic, and working memory locations. It does not specify a retention or sensitive-data exclusion policy.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Automatic learning can retain sensitive task context across skill events.
    Document data minimization, consent, retention limits, and a simple way to inspect and delete memory artifacts before enabling automatic hooks.
  2. FIX-002
    Low
    Manual hook examples execute local shell scripts.
    Keep hook paths fixed and trusted, preserve argument quoting, and instruct users to review the installed skill directory before enabling hooks.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
c43861a65bb95efcae259cd161c9d6f4dc7eec6f
Content hash
a9ee6cbc1e8e0758216490945c4c39be386c0d5eb035dd31dc8a2453a531d8bc
Tree hash
7131ef69ecd1fd361de9703a99315871dcc6ceea5d8d642de1854b7580c247a4
Skill path
skills/charon-fan/self-improving-agent
Audit payload hash
f7c724fb4ae69fbb9f871ca2d7499bf5

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

JSON report Signed attestation CITATION.cff SARIF 2.1.0 Signed installation manifest Source

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: active