The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or metadata.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run the GitHub CLI (gh). It employs security best practices by using single-quoted heredocs (<<'EOF') for multi-line body content, which prevents shell expansion and mitigates command injection risks from the input findings.
[DATA_EXFILTRATION]: Network activity is restricted to the GitHub service via the official CLI. There is no evidence of the skill accessing sensitive local files such as SSH keys, AWS credentials, or environment files.
[PROMPT_INJECTION]: The instructions focus purely on functional logic and do not contain any patterns intended to bypass AI safety guardrails or override system instructions.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: Ingests findings data (SKILL.md).
Boundary markers: None explicitly defined, though structured formatting is requested.
Capability inventory: Bash execution and network interaction via gh CLI (SKILL.md).
Sanitization: Employs shell-safe heredocs to ensure that untrusted data from findings does not affect command execution.

create-github-issues