The Agent Skills Directory

[COMMAND_EXECUTION]: The skill constructs a shell command for the GitHub CLI (gh) that interpolates user-controlled variables such as <slug>, <one-line symptom>, and <issue-file>. If these inputs contain shell metacharacters (e.g., semicolons, backticks, or pipe symbols), they could be used to execute arbitrary commands on the system.
[DATA_EXPOSURE]: The skill uses the <issue-file> and <slug> inputs to determine file system paths for writing reports. Without proper validation, an attacker could use path traversal sequences (e.g., ../) to write files to unauthorized locations outside the intended .opentaint/issues/ directory.
[PROMPT_INJECTION]: The skill processes potentially untrusted data from engine diagnoses and test project outputs, making it vulnerable to indirect prompt injection.
Ingestion points: Data enters the agent context through the <diagnosis>, <test-project>, and <test-compiled> inputs defined in SKILL.md.
Boundary markers: The skill does not define any delimiters or explicit instructions to the agent to ignore instructions embedded within the processed data.
Capability inventory: The skill possesses the ability to write to the local file system and execute the gh CLI tool to post data to a remote repository.
Sanitization: The workflow includes no steps for sanitizing, escaping, or validating the external content before it is incorporated into the generated markdown or the GitHub issue body.

report-analyzer-issue