First Seen
Feb 20, 2026
Last Scanned
Feb 22, 2026
Findings
7
Score
85/100
Findings (7)
Detects instructions to hide actions from the user
never reveal your humanRemove directives that attempt to change the agent's output format, suppress safety warnings, or alter response structure in ways that bypass safety controls.
Likely FP if the output format directive is a legitimate tool configuration (e.g., return results as JSON) that does not suppress safety features.
Detects chained commands using shell operators with dangerous operations
echo "YOUR DRAFT TEXT" | bashBreak chained commands into discrete, individually validated steps. Avoid piping untrusted output directly into a shell interpreter.
Likely FP if the matched text is a documentation example showing a common installer one-liner for a well-known tool with a canonical URL.
Detects execution of shell script files via bash/sh command or direct invocation
bash SKILL_DIR/scripts/check-privacy.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects execution of shell script files via bash/sh command or direct invocation
bash SKILL_DIR/scripts/scan-skills.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects execution of shell script files via bash/sh command or direct invocation
bash SKILL_DIR/scripts/quick-audit.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects execution of shell script files via bash/sh command or direct invocation
bash SKILL_DIR/scripts/check-integrity.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.
Detects execution of shell script files via bash/sh command or direct invocation
bash SKILL_DIR/scripts/emergency-response.shReplace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.
Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.