Claude Code, Skill
Claude Retro Skill
A /retro skill for Claude Code.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
PERMISSION_SHELL_UNDECLARED SECRETS_PATH_CREDENTIAL
Why this grade
- PERMISSION_SHELL_UNDECLARED Medium
Runs shell commands that the manifest or description does not mention.
retro/journal.py, line 162
shutil.rmtree(d, ignore_errors=True) - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
retro/evals/run_evals.py, line 47
shutil.copy(llm.claude_dir() / ".credentials.json", cfg / ".credentials.json")
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
can delete files. requests shell access. No manifest field names shell or command execution.
PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES
retro/journal.py, line 162
shutil.rmtree(d, ignore_errors=True)
retro/llm.py, line 38
r = subprocess.run(cmd, input=prompt, capture_output=True, text=True, encoding="utf-8",
retro/scan.py, line 594
subprocess.Popen([sys.executable, str(Path(__file__).resolve()), *args], stdout=log_f, stderr=log_f,
Show more
retro/evals/run_evals.py, line 89
r = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace",
retro/evals/run_evals.py, line 310
shutil.rmtree(root, ignore_errors=True)
retro/evals/BASELINE.md, line 128
judge was not needed. This rerun also exercises `claude -p` through `subprocess.run(..., shell=False)`
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Pass
No network call found.
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL
retro/evals/run_evals.py, line 47
shutil.copy(llm.claude_dir() / ".credentials.json", cfg / ".credentials.json")
retro/evals/run_evals.py, line 303
cred = cfg / ".credentials.json"
CONTRIBUTING.md, line 22
The evals need a `claude` login file at `~/.claude/.credentials.json`, so they run on Windows and Linux but not on macOS, where the login is kept in the Keychain. A change to `SKIL
Show more
retro/install.md, line 14
The evals copy `~/.claude/.credentials.json` into each sandbox, so they do not run on macOS, where that login is kept in the Keychain and no such file exists. Their output under `e
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 9b6bef8d018a. can delete files. requests shell access. No manifest field names shell or command execution. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 9b6bef8d018a7c824056e091baec707b3b12739b
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.