Versioned security assessment

Report ID: SA-02F077C1

7/5/2026, 6:47:09 AM

context-resume security assessment v8

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
context-resume
Version
v8
Maintainer
Claudate
Source
github.com/Claudate/claude-code-context-sync/tree/main/skills/context-resume
Coverage
1 Files scanned · 179 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require 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.

All static external-command findings are false positives caused by Markdown code fences or inline labels. The skill has no real shell execution, but it does direct the agent to trust session-file content and delete session files when work is complete.

Report position

Latest published report

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

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 179 Lines analyzed

2 items 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.

Not recorded by this audit

Filesystem access

May read or write local files.

Not recorded by this audit

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 16 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:42-63
Untrusted Session Content Can Steer Agent Workflow
The skill tells the agent to read a selected session, display it, then follow the session information and next action notes. A malicious or modified session file could influence later agent behavior if treated as trusted instructions.
The workflow explicitly loads session content and uses it to guide subsequent work. The risk depends on whether session files can be modified by untrusted project content.
RISK-002 Medium
SKILL.md:86-104SKILL.md:150-155
Automatic Session File Deletion
The skill instructs the agent to immediately delete the session file after all unfinished tasks are marked complete. Mistaken task state or an incorrect file selection could cause loss of local progress records.
The deletion behavior is stated directly in the completion step and workflow diagram. The intended path is scoped, but it is still a destructive local file operation.

Remediation

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

  1. FIX-001
    Medium
    Session file content can influence later agent actions.
    Tell the agent to treat session files as untrusted notes, summarize them first, and ask before following sensitive instructions.
  2. FIX-002
    Medium
    Completed session files are deleted immediately.
    Require explicit user confirmation before deletion, or move completed files to an archive directory instead.
  3. FIX-003
    Low
    Full session content is displayed in the conversation.
    Warn users to remove secrets and private data from session files before loading them.

Expert evidence

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

Artifact subject

Marketplace commit
02f077c174c5335e2f5d02ca15e77b70d9543e58
Content hash
4cfc01fbb5c98c7baa74131ba7f9a97c2c4435e454d224a78b629b3507ad060b
Tree hash
86fb2d39b3dd600d1ff211852632783816a88df28aa6b226b5ac8c2edee8fc5f
Skill path
skills/claudate/context-resume
Audit payload hash
7faa6088453d83478f10782aa78ef960

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 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: not_attestable