The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl commands to interact with the MobSF API on localhost for uploading files, initiating scans, and retrieving reports. It also provides a docker command to set up the local environment.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (mobile apps) by parsing MobSF report files, creating a potential surface for indirect prompt injection if the app metadata or code contains malicious instructions.
Ingestion points: upload-response.json, scan-results.json, and mobsf-report.json in SKILL.md.
Boundary markers: No explicit delimiters or warnings are used to separate tool output from instructions.
Capability inventory: The agent uses curl for API interaction and docker for environment setup.
Sanitization: The instructions do not specify any validation or sanitization of the report data before it is presented to the user.

mobile-security-mobsf