📦

Audit History

paper-context-resolver - 5 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v5 LatestAug 8, 2026, 08:58 AM No confirmed findings0No capability change
v4 Jul 6, 2026, 06:30 PM No confirmed findings0No capability change
v3 Jul 6, 2026, 06:30 PM No confirmed findings0External commands
v2 Jun 30, 2026, 07:35 AM No confirmed findings0No capability change
v1 Apr 9, 2026, 08:41 AM No confirmed findings0Baseline

Aug 8, 2026, 08:58 AM

Both static findings are false positives caused by Markdown backticks around a skill slug and a reference path in SKILL.md. No command execution, prompt injection, or other malicious intent was found.

3
Files scanned
105
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (2)
Audited by: codex

Jul 6, 2026, 06:30 PM

The static external command finding is a false positive. SKILL.md uses markdown backticks around a reference file path and does not instruct command execution. No prompt injection, data exfiltration intent, or malicious workflow behavior was found.

3
Files scanned
102
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: codex

Jul 6, 2026, 06:30 PM

The static external command finding is a false positive. SKILL.md uses markdown backticks around a reference file path and does not instruct command execution. No prompt injection, data exfiltration intent, or malicious workflow behavior was found.

3
Files scanned
102
Lines analyzed
1
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (1)
Audited by: codex

Jun 30, 2026, 07:35 AM

Static findings were reviewed and dismissed as false positives. The weak cryptographic algorithm alerts point to descriptive text, and the backtick alert points to a markdown inline file path. No prompt injection, exfiltration behavior, command execution, or malicious intent was found.

3
Files scanned
102
Lines analyzed
0
Review items
3
False positives ignored
Static false positives ignored (3)

These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.

Low
False Positive: Weak Cryptographic Algorithm
The alert at agents/openai.yaml:2 points to a short_description field. It contains plain skill metadata, not cryptographic code or insecure algorithm usage.
The line is YAML metadata text only. There is no hashing, encryption, key handling, or algorithm selection on this line.
Low
False Positive: Markdown Backtick Execution
The alert at SKILL.md:46 is an inline markdown reference to references/paper-assisted-reproduction.md. It is not Ruby code or shell command execution.
The backticks delimit a documentation path in markdown. No interpreter, subprocess call, or user-controlled command string is present.
Low
False Positive: Weak Cryptographic Algorithm
The alert at SKILL.md:3 points to the skill description. It describes research workflow boundaries and does not include cryptographic implementation details.
The line is a natural-language description. No evidence was found for weak cryptography or security-sensitive cryptographic behavior.
No confirmed security findings were recorded for this completed audit.
Audited by: codex

Apr 9, 2026, 08:41 AM

All 3 static analysis findings are false positives. The skill consists only of YAML configuration and markdown documentation files with no executable code. The 'weak cryptographic algorithm' patterns are text matches on non-cryptographic content. The 'external_commands' pattern is a documentation reference to a markdown file, not shell execution. No security risks detected.

3
Files scanned
102
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude