Detecting Eval Exec Usage

What it does

When your agent uses it

• : pre-commit gate on any application that parses user-uploaded code (rule engines
• Formula evaluators
• Plugin systems)
• With: scan eval

Example prompts

• “we run user-supplied expressions.”
• “scan eval”
• “find dynamic exec”
• “/detecting-eval-exec-usage”

Requirements

• Python 3
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Bash(python3:*), Glob, Grep

What it can do on your machine

Read from SKILL.md and the folder at commit 80f86df. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash(python3:*)
  • Glob
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Detecting Eval Exec Usage loads about 1.1k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 180 tokens; SKILL.md has 285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~180

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit 80f86df, republished under its MIT licence (© jeremylongshore). 285 words, ~1,063 tokens.

name

detecting-eval-exec-usage

description

Scan a source tree for dynamic-code-execution APIs that an attacker can hijack: Python eval / exec / compile, JavaScript eval / Function() / setTimeout(string), Ruby eval / instance_eval / class_eval, Java ScriptEngine, PHP eval / assert($str), .NET Activator.CreateInstance / Reflection.Emit with dynamic input. Use when: pre-commit gate on any application that parses user-uploaded code (rule engines, formula evaluators, plugin systems), or post-bug-report when "we run user-supplied expressions." Threshold: any call to eval / exec / Function / similar where the argument is not a string literal. Trigger with: "scan eval", "find dynamic exec", "audit eval calls", "code injection patterns".

allowed-tools

Read, Bash(python3:*), Glob, Grep

compatibility

Designed for Claude Code

disallowed-tools

Bash(rm:*), Bash(curl:*)

version

3.30.0

author

Jeremy Longshore <jeremy@intentsolutions.io>

license

MIT

tags

security, static-analysis, code-injection, pentest

python3 ${CLAUDE_PLUGIN_ROOT}/skills/detecting-eval-exec-usage/scripts/scan_eval.py /path/to/repo

python3 ${CLAUDE_PLUGIN_ROOT}/skills/detecting-eval-exec-usage/scripts/scan_eval.py \
    --min-severity high $(git diff --name-only main...HEAD | tr '\n' ' ')

- run: |
    python3 plugins/security/penetration-tester/skills/detecting-eval-exec-usage/scripts/scan_eval.py \
        . --min-severity high

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/.curated/detecting-eval-exec-usage of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/PLAYBOOK.md
• references/THEORY.md
• scripts/scan_eval.py

Open the folder on GitHubat commit 80f86df