The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to evaluate and audit projects by reading files, history, and observed behavior from a target repository. This creates an attack surface where malicious instructions embedded in the project files could influence the agent's behavior during the assessment process.
Ingestion points: The agent reads fast-track-ai/INDEX.md and inspects files, history, and observed behavior within the target repository (SKILL.md, steps 1 and 3).
Boundary markers: None. The instructions do not specify delimiters or warnings to treat ingested file content as untrusted data.
Capability inventory: The agent can execute a local shell script (fast-track-ai-index.sh) and write files to the fast-track-ai/assessments/ directory.
Sanitization: No sanitization, escaping, or validation of the external project content is mentioned before it is processed by the agent.
[COMMAND_EXECUTION]: The skill invokes a shell script located in a sibling directory using a user-supplied target as an argument.
Evidence: Step 8 in SKILL.md instructs the agent to run ../fast-track-ai-init/scripts/fast-track-ai-index.sh <target>.
Risk: While this appears to be a local utility for the tool suite, executing shell scripts with arguments derived from user input (the 'target') carries a risk of command injection if the agent does not properly validate the target string.

fast-track-ai-assess