The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and processing data from external command-line tools, creating a surface for indirect prompt injection if those tools return malicious content.
Ingestion points: Outputs from aws iam, aws accessanalyzer, gh api, and other CLI tools are captured into variables and files within the collect-soc2-evidence.sh script and GitHub Action workflows in SKILL.md.
Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions in the ingested data.
Capability inventory: The skill uses aws and gh CLI tools to perform network-based API calls, generates filesystem reports, and executes shell scripts (defined in SKILL.md).
Sanitization: There is no evidence of sanitization, escaping, or validation of the data returned by external tools before it is processed or stored.
[DYNAMIC_EXECUTION]: The skill provides a shell script (collect-soc2-evidence.sh) and GitHub Action workflows that dynamically assemble and execute commands based on environment variables and tool outputs.
[COMMAND_EXECUTION]: The skill provides automated bash scripts and GitHub Actions intended to run in a user's environment to collect security and configuration data.

soc2-compliance