The Agent Skills Directory

[COMMAND_EXECUTION]: The skill recommends setting the environment variable GIT_SSL_NO_VERIFY=1 for shell commands in SKILL.md. This disables SSL/TLS certificate verification, which is a security bypass that allows connections to unverified or malicious remote servers.
[DATA_EXFILTRATION]: Disabling SSL verification via GIT_SSL_NO_VERIFY=1 facilitates potential data exfiltration or credential interception, as traffic between the agent and GitHub can be monitored or modified by an attacker through Man-in-the-Middle (MitM) techniques.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of repository content.
Ingestion points: The skill reads commit messages and code differences via git log and git diff in Step 1 of SKILL.md.
Boundary markers: Absent. There are no instructions or delimiters provided to prevent the agent from executing instructions found within the ingested data.
Capability inventory: The skill uses git and gh tools to perform shell execution and network communication as defined in SKILL.md.
Sanitization: Absent. Content from the repository is directly used to populate the PR title and body without validation or sanitization.

create-pr