The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes data from external, untrusted web applications during security assessments.
Ingestion points: The run_assessment function in scripts/agent.py uses the requests library to retrieve headers and body content from arbitrary URLs provided by the user.
Boundary markers: The skill does not implement delimiters or explicit instructions to the agent to disregard potential instructions embedded within the retrieved HTML or HTTP headers.
Capability inventory: The skill possesses capabilities for network communication, local file reading (wordlists), and subprocess execution of the ffuf binary.
Sanitization: No sanitization, escaping, or filtering of the retrieved web content is performed before the data is presented to the agent for analysis.
[COMMAND_EXECUTION]: The script scripts/agent.py utilizes subprocess.run to execute the external utility ffuf.
Evidence: The run_directory_bruteforce function interpolates a user-provided target URL directly into the command arguments for ffuf. While the implementation uses a list-based argument structure to prevent shell-level command injection, the target URL is not validated or sanitized before execution.
[METADATA_POISONING]: There is a discrepancy in the attribution of the skill between different files.
Evidence: The YAML frontmatter in SKILL.md lists the author as "mahipal," whereas the LICENSE file attributes the copyright to "mukul975." This inconsistency in metadata can be misleading regarding the skill's origin and maintenance.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the requests Python package and recommends the use of external tools such as ffuf, sqlmap, and LinkFinder.py.
Evidence: The script scripts/agent.py includes a prompt to the user to execute pip install requests if the dependency is missing. Users are responsible for ensuring these tools are sourced from legitimate and secure repositories.

performing-web-application-penetration-test