Skills/ClawHub/safe-encryption-skill

safe-encryption-skill@0.1.0

CAUTION· install only

Publisher claims: "Encrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher grittygrease · publishing for 271 daysInstalls 2,055Last detonated 23 min ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-18 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; Privileged sudo command; References a credential file in the home directory. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
References a credential file in the home directorySKILL.md:389 · References a credential file in the home directorysafe: using SSH key ~/.ssh/id_ed25519Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Privileged sudo commandSKILL.md:50 · Privileged sudo command — agent may execute with elevated privilegescurl -sL "https://thesafe.dev/downloads/safe-${OS}-${ARCH}" -o safe && chmod +x safe && sudo mv safe /usr/local/bin/; }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
References a credential file in the home directorySKILL.md:423 · References a credential file in the home directorygh ssh-key add ~/.ssh/id_ed25519.pub --title "SAFE Agent Key"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsSKILL.md:382 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files2. `~/.ssh/*` - All SSH private keys in `~/.ssh/` directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
References a credential file in the home directorySKILL.md:418 · References a credential file in the home directory# If you already have ~/.ssh/id_ed25519 or ~/.ssh/id_ecdsa uploaded to GitHub, you're done!Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Privileged sudo commandSKILL.md:38 · Privileged sudo command — agent may execute with elevated privilegescurl -sL https://thesafe.dev/downloads/safe-linux-amd64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandSKILL.md:43 · File permission modification command — agent changes file ownership/permissionscurl -sL https://thesafe.dev/downloads/safe-linux-arm64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:28 · File permission modification command — agent changes file ownership/permissionscurl -sL https://thesafe.dev/downloads/safe-darwin-arm64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
False input termination markerSKILL.md:1289 · False input termination marker — attempts to end user input section-----END X25519 PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
False input termination markerSKILL.md:1301 · False input termination marker — attempts to end user input section-----END X25519 PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
False input termination markerSKILL.md:1304 · False input termination marker — attempts to end user input section-----END ML-KEM-768 PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsSKILL.md:374 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesThe SAFE CLI automatically discovers and uses SSH private keys from `~/.ssh/`:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandSKILL.md:50 · File permission modification command — agent changes file ownership/permissionscurl -sL "https://thesafe.dev/downloads/safe-${OS}-${ARCH}" -o safe && chmod +x safe && sudo mv safe /usr/local/bin/; }Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:397 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Private keys can be in `~/.safe/keys/` (SAFE format) **OR** `~/.ssh/` (OpenSSH format)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandSKILL.md:43 · Privileged sudo command — agent may execute with elevated privilegescurl -sL https://thesafe.dev/downloads/safe-linux-arm64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandSKILL.md:33 · Privileged sudo command — agent may execute with elevated privilegescurl -sL https://thesafe.dev/downloads/safe-darwin-amd64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
False input termination markerSKILL.md:1387 · False input termination marker — attempts to end user input section-----END X25519 PUBLIC KEY-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Reads credential paths from the home directorySKILL.md:418 · Reads credential paths from the home directory# If you already have ~/.ssh/id_ed25519 or ~/.ssh/id_ecdsa uploaded to GitHub, you're done!Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandSKILL.md:33 · File permission modification command — agent changes file ownership/permissionscurl -sL https://thesafe.dev/downloads/safe-darwin-amd64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Privileged sudo commandSKILL.md:28 · Privileged sudo command — agent may execute with elevated privilegescurl -sL https://thesafe.dev/downloads/safe-darwin-arm64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Pipe to network utilitySKILL.md:1499 · Pipe to network utility — potential reverse shellsafe encrypt message.txt -r recipient | nc termbin.com 9999Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
References a credential file in the home directorySKILL.md:422 · References a credential file in the home directoryssh-keygen -t ed25519 -f ~/.ssh/id_ed25519 -N "" -C "safe-agent-key"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsSKILL.md:389 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessafe: using SSH key ~/.ssh/id_ed25519Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandSKILL.md:38 · File permission modification command — agent changes file ownership/permissionscurl -sL https://thesafe.dev/downloads/safe-linux-amd64 -o safe && chmod +x safe && sudo mv safe /usr/local/bin/Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionSKILL.md:1363 · File type combined with upload action — agent may exfiltrate local data filessafe encrypt reply.txt -o reply.safe -r senderFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:1539 · File type combined with upload action — agent may exfiltrate local data filessafe encrypt message.txt -r recipient >> post.txtFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:1354 · File type combined with upload action — agent may exfiltrate local data filesgrep -A2 'BEGIN.*PUBLIC KEY' message.txt > /tmp/sender.pubFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈14,302 tok
1 file · 2 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim grittygrease: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Pipe to network utility≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim grittygreasePropose a patch to the maintainer