CVE-2026-67610: Claude Code Action Bash Tool Exposure
The GitHub Actions workflow allows the Claude AI action to automatically trigger on untrusted pull requests. An attacker can utilize prompt injection in their pull request code to coerce the AI assistant into executing arbitrary shell commands on the runner. This can lead to sensitive secret compromise and unauthorized repository modification. Restrict the j
YAMLgreprules fetch cve-2026-67610-claude-code-action-bash-tool-exposure --engine opengrepDescription
The GitHub Actions workflow allows the Claude AI action to automatically trigger on untrusted pull requests. An attacker can utilize prompt injection in their pull request code to coerce the AI assistant into executing arbitrary shell commands on the runner. This can lead to sensitive secret compromise and unauthorized repository modification. Restrict the j
Community feedback
0 rule-level signals from signed-in users.
- Useful reports
- 0
- Context false positives
- 0
- Metadata suggestions
- 0
Contextual precision
Aggregated from approved scan feedback. False-positive reports describe observed scan contexts, not a global rule verdict.
- Findings observed
- 0
- Projects
- 0
- Reporters
- 0
Precision details are collecting more signed-in reports before verdict counts or ratios are emphasized.
No approved finding verdicts yet.
No scan diagnostics reported yet.